High-quality medical data is critical to the development and implementation of machine learning (ML) algorithms in healthcare; however, security, and privacy concerns continue to limit access. We sought to determine the utility of “synthetic data” in training ML algorithms for the detection of tuberculosis (TB) from inflammatory biomarker profiles. A retrospective dataset (A) comprised of 278 patients was used to generate synthetic datasets (B, C, and D) for training models prior to secondary validation on a generalization dataset. ML models trained and validated on the Dataset A (real) demonstrated an accuracy of 90%, a sensitivity of 89% (95% CI, 83–94%), and a specificity of 100% (95% CI, 81–100%). Models trained using the optimal synthetic dataset B showed an accuracy of 91%, a sensitivity of 93% (95% CI, 87–96%), and a specificity of 77% (95% CI, 50–93%). Synthetic datasets C and D displayed diminished performance measures (respective accuracies of 71% and 54%). This pilot study highlights the promise of synthetic data as an expedited means for ML algorithm development.

Background: Prediction of clinical outcomes for individual cancer patients is an important step in the disease diagnosis and subsequently guides the treatment and patient counseling. In this work, we develop and evaluate a joint outcome and biomarker supervised (estrogen receptor expression and ERBB2 expression and gene amplification) multitask deep learning model for prediction of outcome in breast cancer patients in two nation-wide multicenter studies in Finland (the FinProg and FinHer studies). Our approach combines deep learning with expert knowledge to provide more accurate, robust, and integrated prediction of breast cancer outcomes. Materials and Methods: Using deep learning, we trained convolutional neural networks (CNNs) with digitized tissue microarray (TMA) samples of primary hematoxylin-eosin-stained breast cancer specimens from 693 patients in the FinProg series as input and breast cancer-specific survival as the endpoint. The trained algorithms were tested on 354 TMA patient samples in the same series. An independent set of whole-slide (WS) tumor samples from 674 patients in another multicenter study (FinHer) was used to validate and verify the generalization of the outcome prediction based on CNN models by Cox survival regression and concordance index (c-index). Visual cancer tissue characterization, i.e., number of mitoses, tubules, nuclear pleomorphism, tumor-infiltrating lymphocytes, and necrosis was performed on TMA samples in the FinProg test set by a pathologist and combined with deep learning-based outcome prediction in a multitask algorithm. Results: The multitask algorithm achieved a hazard ratio (HR) of 2.0 (95% confidence interval [CI] 1.30–3.00), P < 0.001, c-index of 0.59 on the 354 test set of FinProg patients, and an HR of 1.7 (95% CI 1.2–2.6), P = 0.003, c-index 0.57 on the WS tumor samples from 674 patients in the independent FinHer series. The multitask CNN remained a statistically independent predictor of survival in both test sets when adjusted for histological grade, tumor size, and axillary lymph node status in a multivariate Cox analyses. An improved accuracy (c-index 0.66) was achieved when deep learning was combined with the tissue characteristics assessed visually by a pathologist. Conclusions: A multitask deep learning algorithm supervised by both patient outcome and biomarker status learned features in basic tissue morphology predictive of survival in a nationwide, multicenter series of patients with breast cancer. The algorithms generalized to another independent multicenter patient series and whole-slide breast cancer samples and provide prognostic information complementary to that of a comprehensive series of established prognostic factors.

Background: The objective of the project was to evaluate the feasibility of introducing a single-networked digital histopathology reporting platform in the Southwest Peninsula region of England by allowing pathologists to experience the technology and recording their perceptions. This information was then used in planning future service development. The project was funded by the National Health Service (NHS) Peninsula Cancer Alliance and took place in 2020 during the COVID-19 pandemic. Materials and Methods: Digital slides of 500 cases from Taunton were reported remotely in Truro, Plymouth, Exeter, Bristol, or Bath by using a single remote reporting platform located on the secure Health and Social Care Network (HSCN) that links NHS sites. These were mainly small gastrointestinal, skin, and gynecological specimens. The digital diagnoses were compared with the diagnoses issued on reporting the glass slides. At the end of the project, the pathologists completed a Google Forms questionnaire of their perceptions of digital pathology. The results were presented at a meeting with the funder and discussed. Results: From the 500 cases there were nine cases of significant diagnostic discrepancy, seven of which involved the misrecognition of Helicobacter pylori in gastric biopsies. The questionnaire at the end of the project showed that there was a general agreement that the platform was easy to use, and the image quality was acceptable. It was agreed that extra work, such as deeper levels, was easy to request on the software platform. Most pathologists did not agree that digital reporting was quicker than glass slide reporting. Some were less confident in their digital diagnoses than glass diagnoses. They agreed that some types of specimens cannot easily be reported digitally. All users indicated that they would like to report at least half of their work digitally in the future if they could, and all strongly agreed that digital pathology would improve access to expert opinions, teaching, and multidisciplinary meetings. It was difficult to find pathologists with time to undertake remote digital reporting, in addition to their existing commitments. Conclusions: Overall, the pathologists developed a positive perception of digital pathology and wished to continue using it.

Background: Human immunodeficiency virus (HIV) screening has improved significantly in the past decade as we have implemented tests that include antigen detection of p24. Incorporation of p24 detection narrows the window from 4 to 2 weeks between infection acquisition and ability to detect infection, reducing unintentional spread of HIV. The fourth- and fifth-generation HIV (HIV5G) screening tests in low prevalence populations have high numbers of false-positive screens and it is unclear if orthogonal testing improves diagnostic and public health outcomes. Methods: We used a cohort of 60,587 HIV5G screening tests with molecular and clinical correlates collected from 2016 to 2018 and applied machine learning to generate a classifier that could predict likely true and false positivity. Results: The best classification was achieved by using support vector machines and transformation of results with principle component analysis. The final classifier had an accuracy of 94% for correct classification of false-positive screens and an accuracy of 92% for classification of true-positive screens. Conclusions: Implementation of this classifier as a screening method for all HIV5G reactive screens allows for improved workflow with likely true positives reported immediately to reduce infection spread and initiate follow-up testing and treatment and likely false positives undergoing orthogonal testing utilizing the same specimen already drawn to reduce distress and follow-up visits. Application of machine learning to the clinical laboratory allows for workflow improvement and decision support to provide improved patient care and public health.

Background: QuPath is an open-source digital image analyzer notable for its user-friendly design, cross-platform compatibility, and customizable functionality. Since it was first released in 2016, at least 624 publications have reported its use, and it has been applied in a wide spectrum of settings. However, there are currently limited reports of its use in placental tissue. Here, we present the use of QuPath to quantify staining of G-protein coupled receptor 18 (GPR18), the receptor for the pro-resolving lipid mediator Resolvin D2, in placental tissue. Methods: Whole slide images of vascular smooth muscle (VSM) and extravillous trophoblast (EVT) cells stained for GPR18 were annotated for areas of interest. Visual scoring was performed on these images by trained and in-training pathologists, while QuPath scoring was performed with the methodology described herein. Results: Bland–Altman analyses showed that, for the VSM category, the two methods were comparable across all staining levels. For EVT cells, the high-intensity staining level was comparable across methods, but the medium and low staining levels were not comparable. Conclusions: Digital image analysis programs offer great potential to revolutionize pathology practice and research by increasing accuracy and decreasing the time and cost of analysis. Careful study is needed to optimize this methodology further.

Background: Artificial intelligence (AI) is fast becoming the tool of choice for scalable and reliable analysis of medical images. However, constraints in sharing medical data outside the institutional or geographical space, as well as difficulties in getting AI models and modeling platforms to work across different environments, have led to a “reproducibility crisis” in digital medicine. Methods: This study details the implementation of a web platform that can be used to mitigate these challenges by orchestrating a digital pathology AI pipeline, from raw data to model inference, entirely on the local machine. We discuss how this federated platform provides governed access to data by consuming the Application Program Interfaces exposed by cloud storage services, allows the addition of user-defined annotations, facilitates active learning for training models iteratively, and provides model inference computed directly in the web browser at practically zero cost. The latter is of particular relevance to clinical workflows because the code, including the AI model, travels to the user's data, which stays private to the governance domain where it was acquired. Results: We demonstrate that the web browser can be a means of democratizing AI and advancing data socialization in medical imaging backed by consumer-facing cloud infrastructure such as Box.com. As a case study, we test the accompanying platform end-to-end on a large dataset of digital breast cancer tissue microarray core images. We also showcase how it can be applied in contexts separate from digital pathology by applying it to a radiology dataset containing COVID-19 computed tomography images. Conclusions: The platform described in this report resolves the challenges to the findable, accessible, interoperable, reusable stewardship of data and AI models by integrating with cloud storage to maintain user-centric governance over the data. It also enables distributed, federated computation for AI inference over those data and proves the viability of client-side AI in medical imaging. Availability: The open-source application is publicly available at https://episphere.github.io/path, with a short video demonstration at https://youtu.be/z59jToy2TxE.

Context: Diseases of the hematopoietic system such as leukemia is diagnosed using bone marrow samples. The cell type distribution plays a major role but requires manual analysis of different cell types in microscopy images. Aims: Automated analysis of bone marrow samples requires detection and classification of different cell types. In this work, we propose and compare algorithms for cell localization, which is a key component in automated bone marrow analysis. Settings and Design: We research fully supervised detection architectures but also propose and evaluate several techniques utilizing weak annotations in a segmentation network. We further incorporate typical cell-like artifacts into our analysis. Whole slide microscopy images are acquired from the human bone marrow samples and annotated by expert hematologists. Subjects and Methods: We adapt and evaluate state-of-the-art detection networks. We further propose to utilize the popular U-Net for cell detection by applying suitable preprocessing steps to the annotations. Statistical Analysis Used: Evaluations are performed on a held-out dataset using multiple metrics based on the two different matching algorithms. Results: The results show that the detection of cells in hematopoietic images using state-of-the-art detection networks yields very accurate results. U-Net-based methods are able to slightly improve detection results using adequate preprocessing – despite artifacts and weak annotations. Conclusions: In this work, we propose, U-Net-based cell detection methods and compare with state-of-the-art detection methods for the localization of hematopoietic cells in high-resolution bone marrow images. We show that even with weak annotations and cell-like artifacts, cells can be localized with high precision.

Background: Tumor heterogeneity is increasingly being recognized as a major source of variability in the histopathological assessment of drug responses. Quantitative analysis of immunohistochemistry (IHC) and immunofluorescence (IF) images using biomarkers that capture spatialpatterns of distinct tumor biology and drug concentration in tumors is of high interest to the field. Methods: We have developed an image analysis pipeline to measure drug response using IF and IHC images along spatial gradients of local drug release from a tumor-implantable drug delivery microdevice. The pipeline utilizes a series of user-interactive python scripts and CellProfiler pipelines with custom modules to perform image and spatial analysis of regions of interest within whole-slide images. Results: Worked examples demonstrate that intratumor measurements such as apoptosis, cell proliferation, and immune cell population density can be quantitated in a spatially and drug concentration-dependent manner, establishing in vivo profiles of pharmacodynamics and pharmacokinetics in tumors. Conclusions: Spatial image analysis of tumor response along gradients of local drug release is achievable in high throughput. The major advantage of this approach is the use of spatially aware annotation tools to correlate drug gradients with drug effects in tumors in vivo.

Background: Accurate and precise alignment of histopathology tissue sections is a key step for the interpretation of the proteome topology and cell level three-dimensional (3D) reconstruction of diseased tissues. However, the realization of an automated and robust method for aligning nonglobally stained immunohistochemical (IHC) sections is still challenging. In this study, we aim to assess the feasibility of multidimensional graph-based image registration on aligning serial-section and whole-slide IHC section images. Materials and Methods: An automated, patch graph-based registration method was established and applied to align serial, whole-slide IHC sections at ×10 magnification (average 32,947 × 27,054 pixels). The alignment began with the initial alignment of high-resolution reference and translated images (object segmentation and rigid registration) and nonlinear registration of low-resolution reference and translated images, followed by the multidimensional graph-based image registration of the segmented patches, and finally, the fusion of deformed patches for inspection. The performance of the proposed method was formulated and evaluated by the Hausdorff distance between continuous image slices. Results: Sets of average 315 patches from five serial whole slide, IHC section images were tested using 21 different IHC antibodies across five different tissue types (skin, breast, stomach, prostate, and soft tissue). The proposed method was successfully automated to align most of the images. The average Hausdorff distance was 48.93 μm with a standard deviation of 14.94 μm, showing a significant improvement from the previously published patch-based nonlinear image registration method (average Hausdorff distance of 93.89 μm with 50.85 μm standard deviation). Conclusions: Our method was effective in aligning whole-slide tissue sections at the cell-level resolution. Further advancements in the screening of the proteome topology and 3D tissue reconstruction could be expected.

Background: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard technique for detection and removal of colorectal lesions with potential to evolve into cancer. When polyps are found in a patient, the current procedure is their complete removal. However, in this process, gastroenterologists cannot assure complete resection and clean margins which are given by the histopathology analysis of the removed tissue, which is performed at laboratory. Aims: In this paper, we demonstrate the capabilities of multiphoton microscopy (MPM) technology to provide imaging biomarkers that can be extracted by deep learning techniques to identify malignant neoplastic colon lesions and distinguish them from healthy, hyperplastic, or benign neoplastic tissue, without the need for histopathological staining. Materials and Methods: To this end, we present a novel MPM public dataset containing 14,712 images obtained from 42 patients and grouped into 2 classes. A convolutional neural network is trained on this dataset and a spatially coherent predictions scheme is applied for performance improvement. Results: We obtained a sensitivity of 0.8228 ± 0.1575 and a specificity of 0.9114 ± 0.0814 on detecting malignant neoplastic lesions. We also validated this approach to estimate the self-confidence of the network on its own predictions, obtaining a mean sensitivity of 0.8697 and a mean specificity of 0.9524 with the 18.67% of the images classified as uncertain. Conclusions: This work lays the foundations for performing in vivo optical colon biopsies by combining this novel imaging technology together with deep learning algorithms, hence avoiding unnecessary polyp resection and allowing in situ diagnosis assessment.

Background: Serous borderline ovarian tumor (SBOT) and high-grade serous ovarian cancer (HGSOC) are two distinct subtypes of epithelial ovarian tumors, with markedly different biologic background, behavior, prognosis, and treatment. However, the histologic diagnosis of serous ovarian tumors can be subjectively variable and labor-intensive as multiple tumor slides/blocks need to be thoroughly examined to search for these features. Materials and Methods: We developed a novel informatics system to facilitate objective and scalable diagnosis screening for SBOT and HGSOC. The system was built upon Groovy scripts and QuPath to enable interactive annotation and data exchange. Results: The system was used to successfully detect cellular boundaries and extract an expanded set of cellular features representing cell- and tissue-level characteristics. The performance of cell-level classification for both tumor and stroma cells achieved >90% accuracy. The performance of differentiating HGSOC versus SBOT achieved 91%–95% accuracy for 6485 imaging patches which have sufficient tumor and stroma cells (minimum of ten each) and 97% accuracy for classifying patients when aggregating the results to whole-slide image based on consensus. Conclusions: Cellular features digitally extracted from pathological images can be used for cell classification and SBOT v. HGSOC differentiation. Introducing digital pathology into ovarian cancer research could be beneficial to discover potential clinical implications. A larger cohort is required to further evaluate the system.

Aims: The study is aimed to verify Aperio AT2 scanner for reporting on the digital pathology platform (DP) and to validate the cohort of pathologists in the interpretation of DP for routine diagnostic histopathological services in Wales, United Kingdom. Materials, Methods and Results: This was a large multicenter study involving seven hospitals across Wales and unique with 22 (largest number) pathologists participating. 7491 slides from 3001 cases were scanned on Leica Aperio AT2 scanner and reported on digital workstations with Leica software of e-slide manager. A senior pathology fellow compared DP reports with authorized reports on glass slide (GS). A panel of expert pathologists reviewed the discrepant cases under multiheader microscope to establish ground truth. 2745 out of 3001 (91%) cases showed complete concordance between DP and GS reports. Two hundred and fifty-six cases showed discrepancies in diagnosis, of which 170 (5.6%) were deemed of no clinical significance by the review panel. There were 86 (2.9%) clinically significant discrepancies in the diagnosis between DP and GS. The concordance was raised to 97.1% after discounting clinically insignificant discrepancies. Ground truth lay with DP in 28 out of 86 clinically significant discrepancies and with GS in 58 cases. Sensitivity of DP was 98.07% (confidence interval [CI] 97.57–98.56%); for GS was 99.07% (CI 98.72–99.41%). Conclusions: We concluded that Leica Aperio AT2 scanner produces adequate quality of images for routine histopathologic diagnosis. Pathologists were able to diagnose in DP with good concordance as with GS. Strengths and Limitations of this Study: Strengths of this study – This was a prospective blind study. Different pathologists reported digital and glass arms at different times giving an ambience of real-time reporting. There was standardized use of software and hardware across Wales. A strong managerial support from efficiency through the technology group was a key factor for the implementation of the study. Limitations: This study did not include Cytopathology and in situ hybridization slides. Difficulty in achieving surgical pathology practise standardization across the whole country contributed to intra-observer variations.

Background: Deep learning diagnostic algorithms are proving comparable results with human experts in a wide variety of tasks, and they still require a huge amount of well-annotated data for training, which is often non affordable. Metric learning techniques have allowed a reduction in the required annotated data allowing few-shot learning over deep learning architectures. Aims and Objectives: In this work, we analyze the state-of-the-art loss functions such as triplet loss, contrastive loss, and multi-class N-pair loss for the visual embedding extraction of hematoxylin and eosin (H&E) microscopy images and we propose a novel constellation loss function that takes advantage of the visual distances of the embeddings of the negative samples and thus, performing a regularization that increases the quality of the extracted embeddings. Materials and Methods: To this end, we employed the public H&E imaging dataset from the University Medical Center Mannheim (Germany) that contains tissue samples from low-grade and high-grade primary tumors of digitalized colorectal cancer tissue slides. These samples are divided into eight different textures (1. tumour epithelium, 2. simple stroma, 3. complex stroma, 4. immune cells, 5. debris and mucus, 6. mucosal glands, 7. adipose tissue and 8. background,). The dataset was divided randomly into train and test splits and the training split was used to train a classifier to distinguish among the different textures with just 20 training images. The process was repeated 10 times for each loss function. Performance was compared both for cluster compactness and for classification accuracy on separating the aforementioned textures. Results: Our results show that the proposed loss function outperforms the other methods by obtaining more compact clusters (Davis-Boulding: 1.41 ± 0.08, Silhouette: 0.37 ± 0.02) and better classification capabilities (accuracy: 85.0 ± 0.6) over H and E microscopy images. We demonstrate that the proposed constellation loss can be successfully used in the medical domain in situations of data scarcity.

A whole-slide imaging (WSI) system is a digital color imaging system used in digital pathology with the potential to substitute the conventional light microscope. A WSI system digitalizes a glass slide by converting the optical image to digital data with a scanner and then converting the digital data back to the optical image with a display. During the digital-to-optical or optical-to-digital conversion, a color space is required to define the mapping between the digital domain and the optical domain so that the numerical data of each color pixel can be interpreted meaningfully. Unfortunately, many current WSI products do not specify the designated color space clearly, which leaves the user using the universally default color space, sRGB. sRGB is a legacy color space that has a limited color gamut, which is known to be unable to reproduce all color shades present in histology slides. In this work, experiments were conducted to quantitatively investigate the limitation of the sRGB color space used in WSI systems. Eight hematoxylin and eosin (H and E)-stained tissue samples, including human bladder, brain, breast, colon, kidney, liver, lung, and uterus, were measured with a multispectral imaging system to obtain the true colors at the pixel level. The measured color truth of each pixel was converted into the standard CIELAB color space to test whether it was within the color gamut of the sRGB color space. Experiment results show that all the eight images have a portion of pixels outside the sRGB color gamut. In the worst-case scenario, the bladder sample, about 35% of the image exceeded the sRGB color gamut. The results suggest that the sRGB color space is inadequate for WSI scanners to encode H and E-stained whole-slide images, and an sRGB display may have insufficient color gamut for displaying H and E-stained histology images.

Background: Clinicopathological scores are used to predict the likelihood of recurrence-free survival for patients with clear cell renal cell carcinoma (ccRCC) after surgery. These are fallible, particularly in the middle range. This inevitably means that a significant proportion of ccRCC patients who will not develop recurrent disease enroll into clinical trials. As an exemplar of using digital pathology, we sought to improve the predictive power of “recurrence free” designation in localized ccRCC patients, by precise measurement of ccRCC nuclear morphological features using computational image analysis, thereby replacing manual nuclear grade assessment. Materials and Methods: TNM 8 UICC pathological stage pT1-pT3 ccRCC cases were recruited in Scotland and in Singapore. A Leibovich score (LS) was calculated. Definiens Tissue studio® (Definiens GmbH, Munich) image analysis platform was used to measure tumor nuclear morphological features in digitized hematoxylin and eosin (H&E) images. Results: Replacing human-defined nuclear grade with computer-defined mean perimeter generated a modified Leibovich algorithm, improved overall specificity 0.86 from 0.76 in the training cohort. The greatest increase in specificity was seen in LS 5 and 6, which went from 0 to 0.57 and 0.40, respectively. The modified Leibovich algorithm increased the specificity from 0.84 to 0.94 in the validation cohort. Conclusions: CcRCC nuclear mean perimeter, measured by computational image analysis, together with tumor stage and size, node status and necrosis improved the accuracy of predicting recurrence-free in the localized ccRCC patients. This finding was validated in an ethnically different Singaporean cohort, despite the different H and E staining protocol and scanner used. This may be a useful patient selection tool for recruitment to multicenter studies, preventing some patients from receiving unnecessary additional treatment while reducing the number of patients required to achieve adequate power within neoadjuvant and adjuvant clinical studies.

Background: Recent advancements in machine learning (ML) bring great possibilities for the development of tools to assist with diagnostic tasks within histopathology. However, these approaches typically require a large amount of ground truth training data in the form of image annotations made by human experts. As such annotation work is a very time-consuming task, there is a great need for tools that can assist in this process, saving time while not sacrificing annotation quality. Methods: In an iterative design process, we developed TissueWand – an interactive tool designed for efficient annotation of gigapixel-sized histopathological images, not being constrained to a predefined annotation task. Results: Several findings regarding appropriate interaction concepts were made, where a key design component was semi-automation based on rapid interaction feedback in a local region. In a user study, the resulting tool was shown to cause substantial speed-up compared to manual work while maintaining quality. Conclusions: The TissueWand tool shows promise to replace manual methods for early stages of dataset curation where no task-specific ML model yet exists to aid the effort.

Context: Several therapeutically important mutations in cancers are economically detected using immunohistochemistry (IHC), which highlights the overexpression of specific antigens associated with the mutation. However, IHC panels can be imprecise and relatively expensive in low-income settings. On the other hand, although hematoxylin and eosin (H&E) staining used to visualize the general tissue morphology is a routine and low cost, it does not highlight any specific antigen or mutation. Aims: Using the human epidermal growth factor receptor 2 (HER2) mutation in breast cancer as an example, we strengthen the case for cost-effective detection and screening of overexpression of HER2 protein in H&E-stained tissue. Settings and Design: We use computational methods that reliably detect subtle morphological changes associated with the over-expression of mutation-specific proteins directly from H&E images. Subjects and Methods: We trained a classification pipeline to determine HER2 overexpression status of H&E stained whole slide images. Our training dataset was derived from a single hospital containing 26 (11 HER2+ and 15 HER2–) cases. We tested the classification pipeline on 26 (8 HER2+ and 18 HER2–) held-out cases from the same hospital and 45 independent cases (23 HER2+ and 22 HER2–) from the TCGA-BRCA cohort. The pipeline was composed of a stain separation module and three deep neural network modules in tandem for robustness and interpretability. Statistical Analysis Used: We evaluate our trained model through area under the curve (AUC)-receiver operating characteristic. Results: Our pipeline achieved an AUC of 0.82 (confidence interval [CI]: 0. 65–0. 98) on held-out cases and an AUC of 0.76 (CI: 0. 61–0. 89) on the independent dataset from TCGA. We also demonstrate the region-level correspondence of HER2 overexpression between a patient's IHC and H&E serial sections. Conclusions: Our work strengthens the case for automatically quantifying the overexpression of mutation-specific proteins in H&E-stained digital pathology, and it highlights the importance of multi-stage machine learning pipelines for added robustness and interpretability.

Introduction: Biomedical and translational research often relies on the evaluation of patients or specimens that meet specific clinical or laboratory criteria. The typical approach used to identify biospecimens is a manual, retrospective process that exists outside the clinical workflow. This often makes biospecimen collection cost prohibitive and prevents the collection of analytes with short stability times. Emerging data architectures offer novel approaches to enhance specimen-identification practices. To this end, we present a new tool that can be deployed in a real-time environment to automate the identification and notification of available biospecimens for biomedical research. Methods: Real-time clinical and laboratory data from Cloverleaf (Infor, NY, NY) were acquired within our computational health platform, which is built on open-source applications. Study-specific filters were developed in NiFi (Apache Software Foundation, Wakefield, MA, USA) to identify the study-appropriate specimens in real time. Specimen metadata were stored in Elasticsearch (Elastic N. V., Mountain View, CA, USA) for visualization and automated alerting. Results: Between June 2018 and December 2018, we identified 2992 unique specimens belonging to 2815 unique patients, split between two different use cases. Based on laboratory policy for specimen retention and study-specific stability requirements, secure E-mail notifications were sent to investigators to automatically notify of availability. The assessment of throughput on commodity hardware demonstrates the ability to scale to approximately 2000 results per second. Conclusion: This work demonstrates that real-world clinical data can be analyzed in real time to increase the efficiency of biospecimen identification with minimal overhead for the clinical laboratory. Future work will integrate additional data types, including the analysis of unstructured data, to enable more complex cases and biospecimen identification.

Background: The Visiopharm human epidermal growth factor receptor 2 (HER2) digital imaging analysis (DIA) algorithm assesses digitized HER2 immunohistochemistry (IHC) by measuring cell membrane connectivity. We aimed to validate this algorithm for clinical use by comparing with pathologists' scoring and correlating with HER2 fluorescence in situ hybridization (FISH) results. Materials and Methods: The study cohort consisted of 612 consecutive invasive breast carcinoma specimens including 395 biopsies and 217 resections. HER2 IHC slides were scanned using Philips IntelliSite Scanners, and the digital images were analyzed using Visiopharm HER2-CONNECT App to obtain the connectivity values (0–1) and scores (0, 1+, 2+, and 3+). HER2 DIA scores were compared with Pathologists' manual scores, and HER2 connectivity values were correlated with HER2 FISH results. Results: The concordance between HER2 DIA scores and pathologists' scores was 87.3% (534/612). All discordant cases (n = 78) were only one-step discordant (negative to equivocal, equivocal to positive, or vice versa). Five cases (0.8%) showed discordant HER2 IHC DIA and HER2 FISH results, but all these cases had relatively low HER2 copy numbers (between 4 and 6). HER2 IHC connectivity showed significantly better correlation with HER2 copy number than HER2/CEP17 ratio. Conclusions: HER2 IHC DIA demonstrates excellent concordance with pathologists' scores and accurately discriminates between HER2 FISH positive and negative cases. HER2 IHC connectivity has better correlation with HER2 copy number than HER2/CEP17 ratio, suggesting HER2 copy number may be more important in predicting HER2 protein expression, and response to anti-HER2-targeted therapy.

Background: Biomarkers in colorectal cancer are scarce, especially for patients with Stage 2 disease. The aim of our study was to identify potential prognostic biomarkers from colorectal cancers using a novel combination of approaches, whereby digital pathology is coupled to shotgun proteomics followed by validation of candidates by immunohistochemistry (IHC) using digital image analysis (DIA). Methods and Results: Tissue cores were punched from formalin-fixed paraffin-embedded colorectal cancers from patients with Stage 2 and 3 disease (n = 26, each). Protein extraction and liquid chromatography-mass spectrometry (MS) followed by analysis using three different methods were performed. Fold changes were evaluated. The candidate biomarker was validated by IHC on a series of 413 colorectal cancers from surgically treated patients using a next-generation tissue microarray. DIA was performed by using a pan-cytokeratin serial alignment and quantifying staining within the tumor and normal tissue epithelium. Analysis was done in QuPath and Brightness_Max scores were used for statistical analysis and clinicopathological associations. MS identified 1947 proteins with at least two unique peptides. To reinforce the validity of the biomarker candidates, only proteins showing a significant (P < 0.05) fold-change using all three analysis methods were considered. Eight were identified, and of these, cathepsin B was selected for further validation. DIA revealed strong associations between higher cathepsin B expression and less aggressive tumor features, including tumor node metastasis stage and lymphatic vessel and venous vessel invasion (P < 0.001, all). Cathepsin B was associated with more favorable survival in univariate analysis only. Conclusions: Our results present a novel approach to biomarker discovery that includes MS and digital pathology. Cathepsin B expression analyzed by DIA within the tumor epithelial compartment was identified as a strong feature of less aggressive tumor behavior and favorable outcome, a finding that should be further investigated on a more functional level.

Background: Digital pathology enables remote access or consults and powerful image analysis algorithms. However, the slide digitization process can create artifacts such as out-of-focus (OOF). OOF is often only detected on careful review, potentially causing rescanning, and workflow delays. Although scan time operator screening for whole-slide OOF is feasible, manual screening for OOF affecting only parts of a slide is impractical. Methods: We developed a convolutional neural network (ConvFocus) to exhaustively localize and quantify the severity of OOF regions on digitized slides. ConvFocus was developed using our refined semi-synthetic OOF data generation process and evaluated using seven slides spanning three different tissue and three different stain types, each of which were digitized using two different whole-slide scanner models ConvFocus's predictions were compared with pathologist-annotated focus quality grades across 514 distinct regions representing 37,700 35 μm × 35 μm image patches, and 21 digitized “z-stack” WSIs that contain known OOF patterns. Results: When compared to pathologist-graded focus quality, ConvFocus achieved Spearman rank coefficients of 0.81 and 0.94 on two scanners and reproduced the expected OOF patterns from z-stack scanning. We also evaluated the impact of OOF on the accuracy of a state-of-the-art metastatic breast cancer detector and saw a consistent decrease in performance with increasing OOF. Conclusions: Comprehensive whole-slide OOF categorization could enable rescans before pathologist review, potentially reducing the impact of digitization focus issues on the clinical workflow. We show that the algorithm trained on our semi-synthetic OOF data generalizes well to real OOF regions across tissue types, stains, and scanners. Finally, quantitative OOF maps can flag regions that might otherwise be misclassified by image analysis algorithms, preventing OOF-induced errors.

Background: Grading of prostatic adenocarcinoma is based on the Gleason scoring system and the more recently established prognostic grade groups. Typically, prostate cancer grading is performed by pathologists based on the morphology of the tumor on hematoxylin and eosin (H and E) slides. In this study, we investigated the histopathological image features with various survival models and attempted to study their correlations. Methods: Three texture methods (speeded-up robust features, histogram of oriented gradient, and local binary pattern) and two convolutional neural network (CNN)-based methods were applied to quantify histopathological image features. Five survival models were assessed on those image features in the context with other prostate clinical prognostic factors, including primary and secondary Gleason patterns, prostate-specific antigen levels, age, and clinical tumor stages. Results: Based on statistical comparisons among different image features with survival models, image features from CNN-based method with a recurrent neural network called CNN-long-short-term memory provided the highest hazard ratio of prostate cancer recurrence under Cox regression with an elastic net penalty. Conclusions: This approach outperformed the other image quantification methods listed above. Using this approach, patient outcomes were highly correlated with the histopathological image features of the tissue samples. In future studies, we plan to investigate the potential use of this approach for predicting recurrence in a wider range of cancer types.

Background: Calculated panel reactive antibody (cPRA) scoring is used to assess whether platelet refractoriness is mediated by human leukocyte antigen (HLA) antibodies in the recipient. cPRA testing uses a national sample of US kidney donors to estimate the population frequency of HLA antigens, which may be different than HLA frequencies within local platelet inventories. We aimed to determine the impact on patient cPRA scores of using HLA frequencies derived from typing local platelet donations rather than national HLA frequencies. Methods: We built an open-source web service to calculate cPRA scores based on national frequencies or custom-derived frequencies. We calculated cPRA scores for every hematopoietic stem cell transplantation (HSCT) patient at our institution based on the United Network for Organ Sharing (UNOS) frequencies and local frequencies. We compared frequencies and correlations between the calculators, segmented by gender. Finally, we put all scores into three buckets (mild, moderate, and high sensitizations) and looked at intergroup movement. Results: 2531 patients that underwent HSCT at our institution had at least 1 antibody and were included in the analysis. Overall, the difference in medians between each group's UNOS cPRA and local cPRA was statistically significant, but highly correlated (UNOS vs. local total: 0.249 and 0.243, ρ = 0.994; UNOS vs. local female: 0.474 and 0.463, ρ = 0.987, UNOS vs. local male: 0.165 and 0.141, ρ = 0.996;P< 0.001 for all comparisons). The median difference between UNOS and cPRA scores for all patients was low (male: 0.014, interquartile range [IQR]: 0.004–0.029; female: 0.0013, IQR: 0.003–0.028). Placement of patients into three groups revealed little intergroup movement, with 2.96% (75/2531) of patients differentially classified. Conclusions: cPRA scores using local frequencies were modestly but significantly different than those obtained using national HLA frequencies. We released our software as open source, so other groups can calculate cPRA scores from national or custom-derived frequencies. Further investigation is needed to determine whether a local-HLA frequency approach can improve outcomes in patients who are immune-refractory to platelets.

Objectives: Barcode-driven workflows reduce patient identification errors. Missing process timestamp data frequently confound our health system's pending lists and appear as actions left undone. Anecdotally, it was noted that missing data could be found when there is procedure noncompliance. This project was developed to determine if missing timestamp data in the histology barcode drive workflow correlated with other process variations, procedure noncompliance, or is an indicator of workflows needing focus for improvement projects.Materials and Methods: Data extracts of timestamp data from January 1, 2018, to December 15, 2018 for the major histology process steps were analyzed for missing data. Case level analysis to determine the presence or absence of expected barcoding events was performed on 1031 surgical pathology cases to determine the cause of the missing data and determine if additional data variations or procedure noncompliance events were present. The data variations were classified according to a scheme defined in the study. Results: Of 70,085, there were 7218 cases (10.3%) with missing process timestamp data. Missing histology process step data was associated with other additional data variations in case-level deep dives (P < 0.0001). Of the cases missing timestamp data in the initial review, 18.4% of the cases had no identifiable cause for the missing data (all expected events took place in the case-level deep dive). Conclusions: Operationally, valuable information can be obtained by reviewing the types and causes of missing data in the anatomic pathology laboratory information system, but only in conjunction with user input and feedback.

Background: Tumor programmed death-ligand 1 (PD-L1) status is useful in determining which patients may benefit from programmed death-1 (PD-1)/PD-L1 inhibitors. However, little is known about the association between PD-L1 status and tumor histopathological patterns. Using deep learning, we predicted PD-L1 status from hematoxylin and eosin (H and E) whole-slide images (WSIs) of nonsmall cell lung cancer (NSCLC) tumor samples. Materials and Methods: One hundred and thirty NSCLC patients were randomly assigned to training (n = 48) or test (n = 82) cohorts. A pair of H and E and PD-L1-immunostained WSIs was obtained for each patient. A pathologist annotated PD-L1 positive and negative tumor regions on the training samples using immunostained WSIs for reference. From the H and E WSIs, over 145,000 training tiles were generated and used to train a multi-field-of-view deep learning model with a residual neural network backbone. Results: The trained model accurately predicted tumor PD-L1 status on the held-out test cohort of H and E WSIs, which was balanced for PD-L1 status (area under the receiver operating characteristic curve [AUC] =0.80, P << 0.01). The model remained effective over a range of PD-L1 cutoff thresholds (AUC = 0.67–0.81, P ≤ 0.01) and when different proportions of the labels were randomly shuffled to simulate interpathologist disagreement (AUC = 0.63–0.77, P ≤ 0.03). Conclusions: A robust deep learning model was developed to predict tumor PD-L1 status from H and E WSIs in NSCLC. These results suggest that PD-L1 expression is correlated with the morphological features of the tumor microenvironment.

Objective: Digital pathology is today a widely used technology, and the digitalization of microscopic slides into whole slide images (WSIs) allows the use of machine learning algorithms as a tool in the diagnostic process. In recent years, “deep learning” algorithms for image analysis have been applied to digital pathology with great success. The training of these algorithms requires a large volume of high-quality images and image annotations. These large image collections are a potent source of information, and to use and share the information, standardization of the content through a consistent terminology is essential. The aim of this project was to develop a pilot dataset of exhaustive annotated WSI of normal and abnormal human tissue and link the annotations to appropriate ontological information. Materials and Methods: Several biomedical ontologies and controlled vocabularies were investigated with the aim of selecting the most suitable ontology for this project. The selection criteria required an ontology that covered anatomical locations, histological subcompartments, histopathologic diagnoses, histopathologic terms, and generic terms such as normal, abnormal, and artifact. WSIs of normal and abnormal tissue from 50 colon resections and 69 skin excisions, diagnosed 2015-2016 at the Department of Clinical Pathology in Linköping, were randomly collected. These images were manually and exhaustively annotated at the level of major subcompartments, including normal or abnormal findings and artifacts. Results: Systemized nomenclature of medicine clinical terms (SNOMED CT) was chosen, and the annotations were linked to its codes and terms. Two hundred WSI were collected and annotated, resulting in 17,497 annotations, covering a total area of 302.19 cm², equivalent to 107,7 gigapixels. Ninety-five unique SNOMED CT codes were used. The time taken to annotate a WSI varied from 45 s to over 360 min, a total time of approximately 360 h. Conclusion: This work resulted in a dataset of 200 exhaustive annotated WSIs of normal and abnormal tissue from the colon and skin, and it has informed plans to build a comprehensive library of annotated WSIs. SNOMED CT was found to be the best ontology for annotation labeling. This project also demonstrates the need for future development of annotation tools in order to make the annotation process more efficient.

Background: Online “e-modules” integrated into medical education may enhance traditional learning. Medical students use e-modules during clinical rotations, but these often lack histopathology correlates of diseases and minimal time is devoted to pathology teaching. To address this gap, we created pediatric pathology case-based e-modules to complement the clinical pediatric curriculum and enhance students' understanding of pediatric diseases. Methods: Philips Tutor is an interactive web-based program in which pediatric pathology e-modules were created with pre-/post-test questions. Each e-module contains a clinical vignette, virtual microscopy, and links to additional resources. Topics were selected based on established learning objectives for pediatric clinical rotations. Pre- and post-tests were administered at the beginning/end of each rotation. Test group had access to the e-modules, but control group did not. Both groups completed the pre/post-tests. Posttest was followed by a feedback survey. Results: Overall, 7% (9/123) in the control group and 8% (13/164) in the test group completed both tests and were included in the analysis. Test group improved their posttest scores by about one point on a 5-point scale (P = 0.01); control group did not (P = 1.00). Students responded that test questions were helpful in assessing their knowledge of pediatric pathology (90%) and experienced relative ease of use with the technology (80%). Conclusions: Students responded favorably to the new technology, but cited time constraints as a significant barrier to study participation. Access to the e-modules suggested an improved posttest score compared to the control group, but pilot data were limited by the small sample size. Incorporating pediatric case-based e-modules with anatomic and clinical pathology topics into the clinical medical education curriculum may heighten students' understanding of important diseases. Our model may serve as a pilot for other medical education platforms.

Background: Professionals and trainees in the medical and scientific fields may receive high e-mail volumes for conferences and journals. In this report, we analyze the amount and characteristics of unsolicited e-mails for journals, conferences, and webinars received by faculty and trainees in a pathology department at an academic medical center. Methods: With informed consent, we analyzed 7 consecutive days of e-mails from faculty and trainees who voluntarily participated in the study and saved unsolicited e-mails from their institutional e-mail address (including junk e-mail folder) for medical/scientific journals, conferences, and webinars. All e-mails were examined for characteristics such as reply receipts, domain name, and spam likelihood. Journal e-mails were specifically analyzed for claims in the message body (for example, peer review, indexing in databases/resources, rapid publication) and actual inclusion in recognized journal databases/resources. Results: A total of 17 faculty (4 assistant, 4 associate, and 9 full professors) and 9 trainees (5 medical students, 2 pathology residents, and 2 pathology fellows) completed the study. A total of 755 e-mails met study criteria (417 e-mails from 328 unique journals, 244 for conferences, and 94 for webinars). Overall, 44.4% of e-mails were flagged as potential spam by the institutional default settings, and 13.8% requested reply receipts. The highest burden of e-mails in 7 days was by associate and full professors (maximum 158 or approximately 8200 per year), although some trainees and assistant professors had over 30 e-mails in 7 days (approximately 1560 per year). Common characteristics of journal e-mails were mention of “peer review” in the message body and low rates of inclusion in recognized journal databases/resources, with 76.4% not found in any of 9 journal databases/resources. The location for conferences in e-mails included 31 different countries, with the most common being the United States (33.2%), Italy (9.8%), China (4.9%), United Kingdom (4.9%), and Canada (4.5%). Conclusions: The present study in an academic pathology department shows a high burden of unsolicited e-mails for medical/scientific journals, conferences, and webinars, especially to associate and full professors. We also demonstrate that some pathology trainees and junior faculty are receiving an estimated 1500 unsolicited e-mails per year.

Background: To assess reproducibility and accuracy of overall Nottingham grade and component scores using digital whole slide images (WSIs) compared to glass slides. Methods: Two hundred and eight pathologists were randomized to independently interpret 1 of 4 breast biopsy sets using either glass slides or digital WSI. Each set included 5 or 6 invasive carcinomas (22 total invasive cases). Participants interpreted the same biopsy set approximately 9 months later following a second randomization to WSI or glass slides. Nottingham grade, including component scores, was assessed on each interpretation, providing 2045 independent interpretations of grade. Overall grade and component scores were compared between pathologists (interobserver agreement) and for interpretations by the same pathologist (intraobserver agreement). Grade assessments were compared when the format (WSI vs. glass slides) changed or was the same for the two interpretations. Results: Nottingham grade intraobserver agreement was highest using glass slides for both interpretations (73%, 95% confidence interval [CI]: 68%, 78%) and slightly lower but not statistically different using digital WSI for both interpretations (68%, 95% CI: 61%, 75%; P= 0.22). The agreement was lowest when the format changed between interpretations (63%, 95% CI: 59%, 68%). Interobserver agreement was significantly higher (P < 0.001) using glass slides versus digital WSI (68%, 95% CI: 66%, 70% versus 60%, 95% CI: 57%, 62%, respectively). Nuclear pleomorphism scores had the lowest inter- and intra-observer agreement. Mitotic scores were higher on glass slides in inter- and intra-observer comparisons. Conclusions: Pathologists' intraobserver agreement (reproducibility) is similar for Nottingham grade using glass slides or WSI. However, slightly lower agreement between pathologists suggests that verification of grade using digital WSI may be more challenging.

Background: Proliferation markers, especially Ki67, are increasingly important in diagnosis and prognosis. The best method for calculating Ki67 is still the subject of debate. Materials and Methods: We evaluated an image analysis tool for quantitative interpretation of Ki67 in neuroendocrine tumors and compared it to manual counts. We expanded a primary digital pathology platform to include the Leica Biosystems image analysis nuclear algorithm. Slides were digitized using a Leica Aperio AT2 Scanner and accessed through the Cerner CoPath LIS interfaced with Aperio eSlideManager through Aperio ImageScope. Selected regions of interest (ROIs) were manually defined and annotated to include tumor cells only; they were then analyzed with the algorithm and by four pathologists counting on printed images. After validation, the algorithm was used to examine the impact of the size and number of areas selected as ROIs. Results: The algorithm provided reproducible results that were obtained within seconds, compared to up to 55 min of manual counting that varied between users. Benefits of image analysis identified by users included accuracy, time savings, and ease of viewing. Access to the algorithm allowed rapid comparisons of Ki67 counts in ROIs that varied in numbers of cells and selection of fields, the outputs demonstrated that the results vary around defined cutoffs that provide tumor grade depending on the number of cells and ROIs counted. Conclusions: Digital image analysis provides accurate and reproducible quantitative data faster than manual counts. However, access to this tool allows multiple analyses of a single sample to use variable numbers of cells and selection of variable ROIs that can alter the result in clinically significant ways. This study highlights the potential risk of hard cutoffs of continuous variables and indicates that standardization of number of cells and number of regions selected for analysis should be incorporated into guidelines for Ki67 calculations.

Background: Accurate diagnosis of melanocytic lesions is challenging, even for expert pathologists. Nowadays, whole-slide imaging (WSI) is used for routine clinical pathology diagnosis in several laboratories. One of the limitations of WSI, as it is most often used, is the lack of a multiplanar focusing option. In this study, we aim to establish the diagnostic accuracy of WSI for melanocytic lesions and investigate the potential accuracy increase of z-stack scanning. Z-stack enables pathologists to use a software focus adjustment, comparable to the fine-focus knob of a conventional light microscope. Materials and Methods: Melanocytic lesions (n = 102) were selected from our pathology archives: 35 nevi, 5 spitzoid tumors of unknown malignant potential, and 62 malignant melanomas, including 10 nevoid melanomas. All slides were scanned at a magnification comparable to use of a ×40 objective, in z-stack mode. A ground truth diagnosis was established on the glass slides by four academic dermatopathologists with a special interest in the diagnosis of melanoma. Six nonacademic surgical pathologists subspecialized in dermatopathology examined the cases by WSI. Results: An expert consensus diagnosis was achieved in 99 (97%) of cases. Concordance rates between surgical pathologists and the ground truth varied between 75% and 90%, excluding nevoid melanoma cases. Concordance rates of nevoid melanoma varied between 10% and 80%. Pathologists used the software focusing option in 7%–28% of cases, which in 1 case of nevoid melanoma resulted in correcting a misdiagnosis after finding a dermal mitosis. Conclusion: Diagnostic accuracy of melanocytic lesions based on glass slides and WSI is comparable with previous publications. A large variability in diagnostic accuracy of nevoid melanoma does exist. Our results show that z-stack scanning, in general, does not increase the diagnostic accuracy of melanocytic.

Whole-slide images (WSIs) are a rich new source of biomedical imaging data. The use of automated systems to classify and segment WSIs has recently come to forefront of the pathology research community. While digital slides have obvious educational and clinical uses, their most exciting potential lies in the application of quantitative computational tools to automate search tasks, assist in classic diagnostic classification tasks, and improve prognosis and theranostics. An essential step in enabling these advancements is to apply advances in machine learning and artificial intelligence from other fields to previously inaccessible pathology datasets, thereby enabling the application of new technologies to solve persistent diagnostic challenges in pathology. Here, we applied convolutional neural networks to differentiate between two forms of melanocytic lesions (Spitz and conventional). Classification accuracy at the patch level was 99.0%–2% when applied to WSI. Importantly, when the model was trained without careful image curation by a pathologist, the training took significantly longer and had lower overall performance. These results highlight the utility of augmented human intelligence in digital pathology applications, and the critical role pathologists will play in the evolution of computational pathology algorithms.

Background: The current technology for remote assessment of fine-needle aspiration-rapid on-site evaluation (FNA-ROSE) is limited. Recent advances may provide solutions. This study compared the performance of VisionTek digital microscope (VDM) (Sakura, Japan) and Hamamatsu NanoZoomer C9600-12 single Z-stack digital scan (SZDS) to conventional light microscopy (CLM) for FNA-ROSE. Methods: We assembled sixty FNA cases from the thyroid (n = 16), lymph node (n = 16), pancreas (n = 9), head and neck (n = 9), salivary gland (n = 5), lung (n = 4), and rectum (n = 1) based on a single institution's routine workflow. One Diff-Quik-stained slide was selected for each case. Two board-certified cytopathologists independently evaluated the cases using VDM, SZDS, and CLM. A “washout” period of at least 14 days was placed between the reviews. The results were categorized into satisfactory versus unsatisfactory for adequacy assessment (AA) and unsatisfactory, benign, atypical, suspicious, and malignant for preliminary diagnosis (PD). Results: For AA, the Cohen's kappa statistics (CKS) scores of intermodality agreement (IMA) were 0.74–0.94 (CLM vs. VDM) and 0.86–1 (CLM vs. SZDS). The discordant rates of IMA were 3.3% (4/120) for VDM versus CLM, and 1.7% (2/120) for SZDS versus CLM. For PD, the CKS scores of IMA ranged 0.7–0.93. The overall discordant rates of IMA were 15% (18/120) for CLM versus VDM and 10.8% (13/120) for CLM versus SZDS. The discordant rates of IMA with 2 or higher degrees were 5.8% (7/120) for CLM versus VDM and 1.7% (2/120) for CLM versus SZDS. The average time spent per slide was 270 s for VDM, significantly longer than that for CLM (113 s) or for SZDS (122 s). Conclusions: Our data demonstrate that both VDM and SZDS are suitable to provide AA and reasonable PD evaluation. VDM, however, has a significantly longer turnaround time and worse diagnostic performance. The study demonstrates both the potentials and challenges of using VDM and SZDS for FNA-ROSE.

Background: Accurate digital pathology image analysis depends on high-quality images. As such, it is imperative to obtain digital images with high resolution for downstream data analysis. While hematoxylin and eosin (H&E)-stained tissue section slides from solid tumors contain three-dimensional information, these data have been ignored in digital pathology. In addition, in cytology and bone marrow aspirate smears, the three-dimensional nature of the specimen has precluded efficient analysis of such morphologic data. An individual image snapshot at a single focal distance is often not sufficient for accurate diagnoses and multiple whole-slide images at different focal distances are necessary for diagnostics. Materials and Methods: We describe a novel computational pipeline and processing program for obtaining a super-resolved image from multiple static images at different z-planes in overlapping but separate frames. This program, MULTI-Z, performs image alignment, Gaussian smoothing, and Laplacian filtering to construct a final super-resolution image from multiple images. Results: We applied this algorithm and program to images of cytology and H&E-stained sections and demonstrated significant improvements in both resolution and image quality by objective data analyses (24% increase in sharpness and focus). Conclusions: With the use of our program, super-resolved images of cytology and H&E-stained tissue sections can be obtained to potentially allow for more optimal downstream computational analysis. This method is applicable to whole-slide scanned images.

Introduction: The development and application of new molecular diagnostic assays based on next-generation sequencing and proteomics require improved methodologies for procurement of target cells from histological sections. Laser microdissection can successfully isolate distinct cells from tissue specimens based on visual selection for many research and clinical applications. However, this can be a daunting task when a large number of cells are required for molecular analysis or when a sizeable number of specimens need to be evaluated. Materials and Methods: To improve the efficiency of the cellular identification process, we describe a microdissection workflow that leverages recently developed and open source image analysis algorithms referred to as computer-aided laser dissection (CALD). CALD permits a computer algorithm to identify the cells of interest and drive the dissection process. Results: We describe several “use cases” that demonstrate the integration of image analytic tools probabilistic pairwise Markov model, ImageJ, spatially invariant vector quantization (SIVQ), and eSeg onto the ThermoFisher Scientific ArcturusXT and Leica LMD7000 microdissection platforms. Conclusions: The CALD methodology demonstrates the integration of image analysis tools with the microdissection workflow and shows the potential impact to clinical and life science applications.

Background: Recent medical education trends encourage the use of teaching strategies that emphasize student centeredness and self-learning. In this context, the use of new educative technologies is stimulated at the Faculty of Medicine of Eduardo Mondlane University (FMUEM) in Mozambique. The Faculty of Medicine of University of Porto (FMUP) and FMUEM have a long-lasting record of collaborative work. Within this framework, both institutions embarked in a partnership, aimed to develop a blended learning course of pathology for undergraduates, shared between the two faculties and incorporating interactive digital microscopy as a central learning tool. Methods: A core team of faculty members from both institutions identified the existing resources and previous experiences in the two faculties. The Moodle course for students from the University of Porto was the basis to implement the current project. The objective was to develop educational modules of mutual interest, designed for e-learning, followed by a voluntary student's survey conducted in FMUEM to get their perception about the process. Results: We selected contents from the pathology curricula of FMUP and FMUEM that were of mutual interest. We next identified and produced new contents for the shared curricula. The implementation involved joint collaboration and training to prepare the new contents, together with building quizzes for self-evaluation. All the practical sessions were based on the use of interactive digital microscopy. The students have reacted enthusiastically to the incorporation of the online component that increased their performance and motivation for pathology learning. For the students in Porto, the major acquisition was the access to slides from infectious diseases as well as autopsy videos. Conclusions: Our study indicates that students benefited from high-quality educational contents, with emphasis on digital microscopy, in a platform generated in a win-win situation for FMUP and FMUEM.

Background: There is an increasing interest in using digitized whole-slide imaging (WSI) for routine surgical pathology diagnoses. Screencasts are digital recordings of computer screen output with advanced interactive features that allow for the preparation of videos. Screencasts that include hyperlinks to WSIs could help teach pathology residents how to become familiar with technologies that they are likely to use in their future career. Materials and Methods: Twenty screencasts were prepared with Camtasia 2.0 software (TechSmith, Okemos, MI, USA). They included clinical history, videos of chest X-rays and/or chest computed tomography images, links to WSI digitized with an Aperio Turbo AT scanner (Leica Biosystems, Buffalo Grove, IL, USA), pre- and posttests, and faculty-narrated videos of the WSI in a manner closely resembling a slide seminar and other educational materials. Screencasts were saved in a hospital network, Screencast.com, YouTube.com, and Vimeo.com. The screencasts were viewed by 12 pathology residents and fellows who made diagnoses, answered the quizzes, and took a survey with questions designed to evaluate their perception of the quality of this technology. Quiz results were automatically e-mailed to faculty. Pre- and posttest results were compared using a paired t-test. Results: Screencasts can be viewed with Windows PC and Mac operating systems and mobile devices; only videos saved in our network and screencast.com could be used to generate quizzes. Participants' feedback was very favorable with average scores ranging from 4.5 to 4.8 (on a scale of 5). Mean posttest scores (87.0% [±21.6%]) were significantly improved over those in the pretest quizzes (48.5% [±31.2%]) (P < 0.0001). Conclusion: Screencasts with WSI that allow residents and fellows to diagnose cases using digital microscopy may prove to be a useful technology to enhance the pathology education. Future studies with larger numbers of screencasts and participants are needed to optimize various teaching strategies.

Background: Whole-slide imaging (WSI) has been implemented in many areas of pathology, but primary diagnostics of cytological specimens are lagging behind. One of the objectives of viewing scanned whole-slide images from histological or cytological specimens is remote exchange of knowledge and expertise of professionals to increase diagnostic accuracy. We compared the scoring results of our team obtained in double readings of two different data sets: conventional light microscopy (CLM) versus CLM and CLM versus WSI. We hypothesized that WSI is noninferior to CLM for primary diagnostics of thin-layer cervical slides. Materials and Methods: First, we determined the concordance rate at different thresholds of the participating cytotechnicians by double reading with CLM of 500 thin-layer cervical slides (Cohort 1). Next, CLM was compared with WSI examination of another 505 thin-layer cervical slides (Cohort 2) scanned at ×20 in single focus plane. Finally, all major discordant cases of Cohort 1 were evaluated by an external expert in the field of gynecological cytology and of Cohort 2 in the weekly case meetings. Results: The overall concordance rate of Cohort 1 (CLM vs. CLM) was 97.8% (95% confidence interval [CI]: 96.0%–98.7%) and of Cohort 2 was 95.3% (95% CI: 93.0%–96.9%). Conclusion: Concordance rates of WSI versus CLM were comparable with those of CLM versus CLM. We have made a step forward paving the road to implementation of WSI also in routine diagnostic cytology.

Background: Workflow and preparation for holding multidisciplinary cancer case reviews (i.e., Tumor Boards) is time-consuming and cumbersome. Use of a software platform might improve this process. This pilot study assessed the impact of a new software platform on tumor board preparation workflow and user satisfaction compared to current methods. Materials and Methods: Using current methods and the NAVIFY Tumor Board Solution, this study assessed the number of tasks and time to prepare tumor board cases. Participants completed online surveys assessing ease of use and satisfaction with current and new platforms. Results: A total of 41 sessions included two surgeons, two oncologists, two pathologists, and two radiologists preparing tumor board cases with 734 tasks were recorded. Overall, there was no difference in the number of tasks using either preparation method (341 current, 393 NAVIFY Tumor Board solution). There was a significant difference in overall preparation time as a function of specialty (F = 71.74, P < 0.0001), with oncologists, radiologists, and surgeons having reduced times with NAVIFY Tumor Board solution compared to the current platform and pathologists having equivalent times. There was a significant difference (F = 38.98, P < 0.0001) for times as a function of task category. Review of clinical course data and other preparation tasks decreased significantly, but pathology and radiology review did not differ significantly. The new platform received higher ratings than the current methods on all survey questions regarding the ease of use and satisfaction. Conclusions: The study supported the hypothesis that the new software platform can improve Tumor Board preparation. Further study is needed to assess the impact of this platform in different hospitals, different data storage systems, with different observers, and different types of Tumor board cases as well as its impact on the quality of the tumor board discussion.

Background: Neuroblastoma is the most common extracranial solid tumor in children younger than 5 years old. Optimal management of neuroblastic tumors depends on many factors including histopathological classification. The gold standard for classification of neuroblastoma histological images is visual microscopic assessment. In this study, we propose and evaluate a deep learning approach to classify high-resolution digital images of neuroblastoma histology into five different classes determined by the Shimada classification. Subjects and Methods: We apply a combination of convolutional deep belief network (CDBN) with feature encoding algorithm that automatically classifies digital images of neuroblastoma histology into five different classes. We design a three-layer CDBN to extract high-level features from neuroblastoma histological images and combine with a feature encoding model to extract features that are highly discriminative in the classification task. The extracted features are classified into five different classes using a support vector machine classifier. Data: We constructed a dataset of 1043 neuroblastoma histological images derived from Aperio scanner from 125 patients representing different classes of neuroblastoma tumors. Results: The weighted average F-measure of 86.01% was obtained from the selected high-level features, outperforming state-of-the-art methods. Conclusion: The proposed computer-aided classification system, which uses the combination of deep architecture and feature encoding to learn high-level features, is highly effective in the classification of neuroblastoma histological images.

Background: Numerous studies have revealed widespread clinician frustration with the usability of electronic health records (EHRs) that is counterproductive to adoption of EHR systems to meet the aims of health-care reform. With poor system usability comes increased risk of negative unintended consequences. Usability issues could lead to user error and workarounds that have the potential to compromise patient safety and negatively impact the quality of care.^[1] While there is ample research on EHR usability, there is little information on the usability of laboratory information systems (LISs). Yet, LISs facilitate the timely provision of a great deal of the information needed by physicians to make patient care decisions.^[2] Medical and technical advances in genomics that require processing of an increased volume of complex laboratory data further underscore the importance of developing user-friendly LISs. This study aims to add to the body of knowledge on LIS usability. Methods: A survey was distributed among LIS users at hospitals across the United States. The survey consisted of the ten-item System Usability Scale (SUS). In addition, participants were asked to rate the ease of performing 24 common tasks with a LIS. Finally, respondents provided comments on what they liked and disliked about using the LIS to provide diagnostic insight into LIS perceived usability. Results: The overall mean SUS score of 59.7 for the LIS evaluated is significantly lower than the benchmark of 68 (P < 0.001). All LISs evaluated received mean SUS scores below 68 except for Orchard Harvest (78.7). While the years of experience using the LIS was found to be a statistically significant influence on mean SUS scores, the combined effect of years of experience and LIS used did not account for the statistically significant difference in the mean SUS score between Orchard Harvest and each of the other LISs evaluated. Conclusions: The results of this study indicate that overall usability of LISs is poor. Usability lags that of systems evaluated across 446 usability surveys.

Background: The first satellite center to offer interventional radiology procedures at Memorial Sloan Kettering Cancer Center opened in October 2014. Two of the procedures offered, fine needle aspirations and core biopsies, required a rapid on-site cytologic evaluation of smears and biopsy touch imprints for cellular content and adequacy. The volume and frequency of such evaluations did not justify hiring on-site cytotechnologists, and therefore, a dynamic robotic telecytology (TC) solution was created. In this article, we provide data on our experience with this active implementation. Sakura VisionTek was selected as our robotic TC solution. Methods: A retrospective analysis of all TC evaluations from this satellite site was performed. Information was collected on demographics, lesion location, imaging modality; a comparison of TC-assisted adequacy with final adequacy was also conducted. Results: An analysis of 439 cases was performed over a period of 23 months with perfect correlation in 92.7% (407/439) of the cases. An adequacy upgrade (inadequate specimen becomes adequate) in 6.6% (29/439) of the cases. An adequacy downgrade (adequate specimen becomes inadequate), is near zero at 0.7% (3/439) of the cases. Conclusions: Dynamic robotic TC is effective for immediate evaluations performed without on-site cytotechnology staff. The overall intent of this article is to present data and concordance rates as outcome metrics. Thus far, such outcome metrics have exceeded our expectations. Our TC implementation shows high, perfect concordance. Adequacy upgrades are minor but more relevant and impressive is a near zero adequacy downgrade. Our full implementation has been so successful that plans are in place for configurations at future satellite sites.

Background: The use of minimally invasive procedures to obtain material for diagnostic purposes has become more prevalent in recent years. As such, there is increased demand for immediate cytologic adequacy assessment of minimally invasive procedures. The array of different locations in which rapid on-site evaluation (ROSE) is expected requires an ever-increasing number of cytology personnel to provide support for adequacy assessment. In our study, we describe the implementation process of a telecytology (TC) system in a high case volume setting and evaluate the performance of this activity. Methods: We performed retrospectively an analysis of all consecutive remote TC ROSE evaluations obtained for 15 months. The specimens were evaluated using a TC system. The ROSE adequacy assessment obtained at the time of the procedure was compared to the final cytopathologist-rendered adequacy assessment when all the material was available for review, including the alcohol-fixed preparations. Results: A total of 8106 distinct cases were analyzed. TC-assisted preliminary adequacy assessment was highly concordant with the final cytopathologist-rendered adequacy assessment. Perfect concordance or accuracy was at 93.1% (7547/8106). The adequacy upgrade rate (inadequate specimen became adequate) was 6.8% (551/8106), and the initial adequacy downgrade (adequate specimen became inadequate) was <0.1% (8/8106). Conclusions: The TC outcome demonstrates high concordance between the initial adequacy assessment and final cytopathologist-rendered adequacy assessment. Adequacy upgrades were minor but, more importantly, our results demonstrate a minimal adequacy downgrade. The process implemented effectively eliminated the need for an attending pathologist to be physically present onsite during a biopsy procedure.

Context: Within digital pathology, digitalization of the grossing procedure has been relatively underexplored in comparison to digitalization of pathology slides. Aims: Our investigation focuses on the interaction design of an augmented reality gross pathology workstation and refining the interface so that information and visualizations are easily recorded and displayed in a thoughtful view. Settings and Design: The work in this project occurred in two phases: the first phase focused on implementation of an augmented reality grossing workstation prototype while the second phase focused on the implementation of an incremental prototype in parallel with a deeper design study. Subjects and Methods: Our research institute focused on an experimental and “designerly” approach to create a digital gross pathology prototype as opposed to focusing on developing a system for immediate clinical deployment. Statistical Analysis Used: Evaluation has not been limited to user tests and interviews, but rather key insights were uncovered through design methods such as “rapid ethnography” and “conversation with materials”. Results: We developed an augmented reality enhanced digital grossing station prototype to assist pathology technicians in capturing data during examination. The prototype uses a magnetically tracked scalpel to annotate planned cuts and dimensions onto photographs taken of the work surface. This article focuses on the use of qualitative design methods to evaluate and refine the prototype. Our aims were to build on the strengths of the prototype's technology, improve the ergonomics of the digital/physical workstation by considering numerous alternative design directions, and to consider the effects of digitalization on personnel and the pathology diagnostics information flow from a wider perspective. A proposed interface design allows the pathology technician to place images in relation to its orientation, annotate directly on the image, and create linked information. Conclusions: The augmented reality magnetically tracked scalpel reduces tool switching though limitations in today's augmented reality technology fall short of creating an ideal immersive workflow by requiring the use of a monitor. While this technology catches up, we recommend focusing efforts on enabling the easy creation of layered, complex reports, linking, and viewing information across systems. Reflecting upon our results, we argue for digitalization to focus not only on how to record increasing amounts of data but also how these data can be accessed in a more thoughtful way that draws upon the expertise and creativity of pathology professionals using the systems.

Chronic kidney disease (CKD) is one of the life-threatening diseases. Early detection and proper management are solicited for augmenting survivability. As per the UCI data set, there are 24 attributes for predicting CKD or non-CKD. At least there are 16 attributes need pathological investigations involving more resources, money, time, and uncertainties. The objective of this work is to explore whether we can predict CKD or non-CKD with reasonable accuracy using less number of features. An intelligent system development approach has been used in this study. We attempted one important feature selection technique to discover reduced features that explain the data set much better. Two intelligent binary classification techniques have been adopted for the validity of the reduced feature set. Performances were evaluated in terms of four important classification evaluation parameters. As suggested from our results, we may more concentrate on those reduced features for identifying CKD and thereby reduces uncertainty, saves time, and reduces costs.

Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.

Background: Digital whole slide imaging may be useful for obtaining second opinions and is used in many countries. However, the U.S. Food and Drug Administration requires verification studies. Methods: Pathologists were randomized to interpret one of four sets of breast biopsy cases during two phases, separated by ≥9 months, using glass slides or digital format (sixty cases per set, one slide per case, n = 240 cases). Accuracy was assessed by comparing interpretations to a consensus reference standard. Intraobserver reproducibility was assessed by comparing the agreement of interpretations on the same cases between two phases. Estimated probabilities of confirmation by a reference panel (i.e., predictive values) were obtained by incorporating data on the population prevalence of diagnoses. Results: Sixty-five percent of responding pathologists were eligible, and 252 consented to randomization; 208 completed Phase I (115 glass, 93 digital); and 172 completed Phase II (86 glass, 86 digital). Accuracy was slightly higher using glass compared to digital format and varied by category: invasive carcinoma, 96% versus 93% (P = 0.04); ductal carcinoma in situ (DCIS), 84% versus 79% (P < 0.01); atypia, 48% versus 43% (P = 0.08); and benign without atypia, 87% versus 82% (P < 0.01). There was a small decrease in intraobserver agreement when the format changed compared to when glass slides were used in both phases (P = 0.08). Predictive values for confirmation by a reference panel using glass versus digital were: invasive carcinoma, 98% and 97% (not significant [NS]); DCIS, 70% and 57% (P = 0.007); atypia, 38% and 28% (P = 0.002); and benign without atypia, 97% and 96% (NS). Conclusions: In this large randomized study, digital format interpretations were similar to glass slide interpretations of benign and invasive cancer cases. However, cases in the middle of the spectrum, where more inherent variability exists, may be more problematic in digital format. Future studies evaluating the effect these findings exert on clinical practice and patient outcomes are required.

Background: Recent studies of molecular biology have provided great advances for diagnostic molecular pathology. Automated diagnostic systems with computerized scanning for sampled cells in fluids or smears are now widely utilized. Automated analysis of tissue sections is, however, very difficult because they exhibit a complex mixture of overlapping malignant tumor cells, benign host-derived cells, and extracellular materials. Thus, traditional histological diagnosis is still the most powerful method for diagnosis of diseases. Methods: We have developed a novel computer-assisted pathology system for rapid, automated histological analysis of hematoxylin and eosin (H and E)-stained sections. It is a multistage recognition system patterned after methods that human pathologists use for diagnosis but harnessing machine learning and image analysis. The system first analyzes an entire H and E-stained section (tissue) at low resolution to search suspicious areas for cancer and then the selected areas are analyzed at high resolution to confirm the initial suspicion. Results: After training the pathology system with gastric tissues samples, we examined its performance using other 1905 gastric tissues. The system's accuracy in detecting malignancies was shown to be almost equal to that of conventional diagnosis by expert pathologists. Conclusions: Our novel computerized analysis system provides a support for histological diagnosis, which is useful for screening and quality control. We consider that it could be extended to be applicable to many other carcinomas after learning normal and malignant forms of various tissues. Furthermore, we expect it to contribute to the development of more objective grading systems, immunohistochemical staining systems, and fluorescent-stained image analysis systems.

Background: The opportunity offered by whole slide scanners of automated histological analysis implies an ever increasing importance of digital pathology. To go beyond the importance of conventional pathology, however, digital pathology may need a basic histological starting point similar to that of hematoxylin and eosin staining in conventional pathology. This study presents an automated fluorescence-based microscopy approach providing highly detailed morphological data from unstained microsections. This data may provide a basic histological starting point from which further digital analysis including staining may benefit. Methods: This study explores the inherent tissue fluorescence, also known as autofluorescence, as a mean to quantitate cardiac tissue components in histological microsections. Data acquisition using a commercially available whole slide scanner and an image-based quantitation algorithm are presented. Results: It is shown that the autofluorescence intensity of unstained microsections at two different wavelengths is a suitable starting point for automated digital analysis of myocytes, fibrous tissue, lipofuscin, and the extracellular compartment. The output of the method is absolute quantitation along with accurate outlines of above-mentioned components. The digital quantitations are verified by comparison to point grid quantitations performed on the microsections after Van Gieson staining. Conclusion: The presented method is amply described as a prestain multicomponent quantitation and outlining tool for histological sections of cardiac tissue. The main perspective is the opportunity for combination with digital analysis of stained microsections, for which the method may provide an accurate digital framework.

Introduction: Centralization of cancer treatment entails a reassessment of the diagnostic tissue specimens. Packaging and shipment of glass slides from the local to the central pathology unit means that the standard procedure is time-consuming and that it is difficult to comply with governmental requirements. The aim was to evaluate whether real-time digital microscopy for urological cancer specimens during the primary diagnostic process can replace subsequent physical slide referral and reassessment without compromising diagnostic safety. Methods: From May to October 2014, tissue specimens from 130 patients with urological cancer received at Næstved Hospital's Pathology Department, and expected to be referred for further treatment at cancer unit of a university hospital, were diagnosed using standard light microscopy. In the event of diagnostic uncertainty, the VisionTek digital microscope (Sakura Finetek) was employed. The Pathology Department at Næstved Hospital was equipped with a digital microscope and three consultant pathologists were stationed at Rigshospitalet with workstations optimized for digital microscopy. Representative slides for each case were selected for consultation and live digital consultation took place over the telephone using remote access software. Time of start and finish for each case was logged. For the physically referred cases, time from arrival to sign-out was logged in the national pathology information system, and time spent on microscopy and reporting was noted manually. Diagnosis, number of involved biopsies, grade, and stage were compared between digital microscopy and conventional microscopy. Results: Complete data were available for all 130 cases. Standard procedure with referral of urological cancer specimens took a mean of 8 min 56 s for microscopy, reporting and sign-out per case. For live digital consultations, a mean of 18 min 37 s was spent on each consultation with 4 min 43 s for each case, depending on the number of digital slides included. Only in two cases could a consensus regarding the diagnosis not be reached during live consultation; this did not, it should be noted, affect patient treatment. Complete agreement between conventional and digital histopathology diagnosis was reached in all the 53 patients referred to central pathology units. The participating pathologists were in general comfortable using live digital microscopy, but they emphasized that a fast internet connection was essential for a smooth consultation. Discussion and Conclusion: An almost perfect agreement between live digital and conventional microscopy was observed in this study. Live digital consultation allowed cases to be referred from local hospitals to central cancer units without the standard delay caused by shipment. Only a few preselected specimen slides for each patient were presented in live consultation, which reduced the time spent on diagnosis compared to using the conventional method. Implementation of real-time digital microscopy would result in quicker turnaround and patient referral time, and with careful selection of relevant specimen slides for consultation, diagnostic safety would not be compromised.

This paper describes work presented at the Nordic Symposium on Digital Pathology 2015, in Linköping, Sweden. Prostatic intraepithelial neoplasia (PIN) represents premalignant tissue involving epithelial growth confined in the lumen of prostatic acini. In the attempts to understand oncogenesis in the human prostate, early neoplastic changes can be modeled in the mouse with genetic manipulation of certain tumor suppressor genes or oncogenes. As with many early pathological changes, the PIN lesions in the mouse prostate are macroscopically small, but microscopically spanning areas often larger than single high magnification focus fields in microscopy. This poses a challenge to utilize full potential of the data acquired in histological specimens. We use whole prostates fixed in molecular fixative PAXgene™, embedded in paraffin, sectioned through and stained with H&E. To visualize and analyze the microscopic information spanning whole mouse PIN (mPIN) lesions, we utilize automated whole slide scanning and stacked sections through the tissue. The region of interests is masked, and the masked areas are processed using a cascade of automated image analysis steps. The images are normalized in color space, after which exclusion of secretion areas and feature extraction is performed. Machine learning is utilized to build a model of early PIN lesions for determining the probability for histological changes based on the calculated features. We performed a feature-based analysis to mPIN lesions. First, a quantitative representation of over 100 features was built, including several features representing pathological changes in PIN, especially describing the spatial growth pattern of lesions in the prostate tissue. Furthermore, we built a classification model, which is able to align PIN lesions corresponding to grading by visual inspection to more advanced and mild lesions. The classifier allowed both determining the probability of early histological changes for uncategorized tissue samples and interpretation of the model parameters. Here, we develop quantitative image analysis pipeline to describe morphological changes in histological images. Even subtle changes in mPIN lesion characteristics can be described with feature analysis and machine learning. Constructing and using multidimensional feature data to represent histological changes enables richer analysis and interpretation of early pathological lesions.

Background: Intraductal proliferative lesions (IDPLs) of the breast are recognized as a risk factor for subsequent invasive carcinoma development. Although opportunities for IDPL diagnosis have increased, these lesions are difficult to diagnose correctly, especially atypical ductal hyperplasia (ADH) and low-grade ductal carcinoma in situ (LG-DCIS). In order to define the difference between these lesions, many molecular pathological approaches have been performed. However, still we do not have a molecular marker and objective histological index about IDPLs of the breast. Methods: We generated full digital pathology archives from 175 female IDPL patients, including usual ductal hyperplasia (UDH), ADH, LG-DCIS, intermediate-grade (IM)-DCIS, and high-grade (HG)-DCIS. After total 2,035,807 nucleic segmentations were extracted, we evaluated nuclear features using step-wise linear discriminant analysis (LDA) and a support vector machine. Results: High diagnostic accuracy (81.8–99.3%) was achieved between pathologists' diagnoses and two-group LDA predictions from nucleic features for IDPL discrimination. Grouping of nuclear features as size and shape-related or intranuclear texture-related revealed that the latter group was more important when distinguishing between normal duct, UDH, ADH, and LG-DCIS. However, these two groups were equally important when discriminating between LG-DCIS and HG-DCIS. The Mahalanobis distances between each group showed that the smallest distance values occurred between LG-DCIS and IM-DCIS and between ADH and Normal. On the other hand, the distance value between ADH and LG-DCIS was larger than this distance. Conclusions: In this study, we have presented a practical and useful digital pathological method that incorporates nuclear morphological and textural features for IDPL prediction. We expect that this novel algorithm is used for the automated diagnosis assisting system for breast cancer.

Background: DNA mixtures of two or more people are a common type of forensic crime scene evidence. A match statistic that connects the evidence to a criminal defendant is usually needed for court. Jurors rely on this strength of match to help decide guilt or innocence. However, the reliability of unsophisticated match statistics for DNA mixtures has been questioned. Materials and Methods: The most prevalent match statistic for DNA mixtures is the combined probability of inclusion (CPI), used by crime labs for over 15 years. When testing 13 short tandem repeat (STR) genetic loci, the CPI ^-1 value is typically around a million, regardless of DNA mixture composition. However, actual identification information, as measured by a likelihood ratio (LR), spans a much broader range. This study examined probability of inclusion (PI) mixture statistics for 517 locus experiments drawn from 16 reported cases and compared them with LR locus information calculated independently on the same data. The log(PI ^-1 ) values were examined and compared with corresponding log(LR) values. Results: The LR and CPI methods were compared in case examples of false inclusion, false exclusion, a homicide, and criminal justice outcomes. Statistical analysis of crime laboratory STR data shows that inclusion match statistics exhibit a truncated normal distribution having zero center, with little correlation to actual identification information. By the law of large numbers (LLN), CPI ^-1 increases with the number of tested genetic loci, regardless of DNA mixture composition or match information. These statistical findings explain why CPI is relatively constant, with implications for DNA policy, criminal justice, cost of crime, and crime prevention. Conclusions: Forensic crime laboratories have generated CPI statistics on hundreds of thousands of DNA mixture evidence items. However, this commonly used match statistic behaves like a random generator of inclusionary values, following the LLN rather than measuring identification information. A quantitative CPI number adds little meaningful information beyond the analyst's initial qualitative assessment that a person's DNA is included in a mixture. Statistical methods for reporting on DNA mixture evidence should be scientifically validated before they are relied upon by criminal justice.

Background: Identifying new and more robust assessments of proficiency/expertise (finding new "biomarkers of expertise") in histopathology is desirable for many reasons. Advances in digital pathology permit new and innovative tests such as flash viewing tests and eye tracking and slide navigation analyses that would not be possible with a traditional microscope. The main purpose of this study was to examine the usefulness of time-restricted testing of expertise in histopathology using digital images. Methods: 19 novices (undergraduate medical students), 18 intermediates (trainees), and 19 experts (consultants) were invited to give their opinion on 20 general histopathology cases after 1 s and 10 s viewing times. Differences in performance between groups were measured and the internal reliability of the test was calculated. Results: There were highly significant differences in performance between the groups using the Fisher's least significant difference method for multiple comparisons. Differences between groups were consistently greater in the 10-s than the 1-s test. The Kuder-Richardson 20 internal reliability coefficients were very high for both tests: 0.905 for the 1-s test and 0.926 for the 10-s test. Consultants had levels of diagnostic accuracy of 72% at 1 s and 83% at 10 s. Conclusions: Time-restricted tests using digital images have the potential to be extremely reliable tests of diagnostic proficiency in histopathology. A 10-s viewing test may be more reliable than a 1-s test. Over-reliance on "at a glance" diagnoses in histopathology is a potential source of medical error due to over-confidence bias and premature closure.

Background: Increasingly, as in our institution, operating rooms are located in hospitals and the pathology suite is located at a distant location because of off-site consolidation of pathology services. Telepathology is a technology which bridges the gap between pathologists and offers a means to obtain a consultation remotely. We aimed to evaluate the utility of telepathology as a means to assist the pathologist at the time of intraoperative consultation of lung nodules when a subspecialty pathologist is not available to directly review the slide. Methods: Cases of lung nodules suspicious for a neoplasm were included. Frozen sections were prepared in the usual manner. The pathologists on the intraoperative consultation service at two of our system hospitals notified the thoracic pathologist of each case after rendering a preliminary diagnosis. The consultation was performed utilizing a Nikon™ Digital Sight camera and web-based Remote Medical Technologies™ software with live video streaming directed by the host pathologist. The thoracic pathologist rendered a diagnosis without knowledge of the preliminary interpretation then discussed the interpretation with the frozen section pathologist. The interpretations were compared with the final diagnosis rendered after sign-out. Results: One hundred and three consecutive cases were included. The frozen section pathologist and a thoracic pathologist had concordant diagnoses in 93 cases (90.2%), discordant diagnoses in nine cases (8.7%), and one case in which both deferred. There was an agreement between the thoracic pathologist's diagnosis and the final diagnosis in 98% of total cases including 8/9 (88.9%) of the total discordant cases. In two cases, if the thoracic pathologist had not been consulted, the patient would have been undertreated. Conclusions: We have shown that telepathology is an excellent consultation tool in the frozen section diagnosis of lung nodules.

Introduction: Cervical cancer is one of the most common causes of death in women worldwide. ^[1] The introduction of cervical cytology in screening programs is an effective way for early detection and treatment of cervical precancerous lesions. Conventional screening of cervical cytology slides is still considered the current "gold standard" for the assessment of proficiency in becoming a cytotechnician, but diagnosis using digital whole slide images (WSI) may offer many advantages. Materials and Methods: In this study, we have used a selection of WSI from thin-layer specimens of the most common cervical infections and (pre) neoplastic lesions, and hypothesized that weekly WSI based case-meetings would help to obtain optimal acceptance of the new digital workflow in daily pathology practice. A questionnaire, before and after the test period was used to study the effect of our approach. Results: The participants clearly had to go through a learning curve to get accustomed to viewing WSI. In the beginning, there was a little self-confidence in recognizing classical cervical cytomorphological features in the WSI, and there were complaints about the speed of viewing and insufficient Z-resolution for cell groups. Adjusting the Z-stack settings resulted in better three-dimensional information due to better focusing options. Weekly meetings appeared to be instrumental in the implementation process, as participants had to select and present WSI from thematic cases themselves, and thereby, got used to viewing WSI. Some WSI were replaced by better ones until a final set of 45 representatives WSI remained. Eventually, the consensus was reached among all participants that cytomorphological features in WSI from thin-layers cervical specimens could comparably be appreciated in WSI as by conventional microscopy. The selection of 45 WSI was now used to create a digital WSI based reference atlas to support further studies. Conclusion: We have obtained consensus between professionals that WSI from cervical cytology can be used to identify cytomorphological features, necessary for diagnosis. In addition, we observed that active participation of professionals had a positive effect on the overall acceptance of WSI and was important in the change management.

Background: Structural reporting enables semantic understanding and prompt retrieval of clinical findings about patients. While synoptic pathology reporting provides templates for data entries, information in pathology reports remains primarily in narrative free text form. Extracting data of interest from narrative pathology reports could significantly improve the representation of the information and enable complex structured queries. However, manual extraction is tedious and error-prone, and automated tools are often constructed with a fixed training dataset and not easily adaptable. Our goal is to extract data from pathology reports to support advanced patient search with a highly adaptable semi-automated data extraction system, which can adjust and self-improve by learning from a user's interaction with minimal human effort. Methods : We have developed an online machine learning based information extraction system called IDEAL-X. With its graphical user interface, the system's data extraction engine automatically annotates values for users to review upon loading each report text. The system analyzes users' corrections regarding these annotations with online machine learning, and incrementally enhances and refines the learning model as reports are processed. The system also takes advantage of customized controlled vocabularies, which can be adaptively refined during the online learning process to further assist the data extraction. As the accuracy of automatic annotation improves overtime, the effort of human annotation is gradually reduced. After all reports are processed, a built-in query engine can be applied to conveniently define queries based on extracted structured data. Results: We have evaluated the system with a dataset of anatomic pathology reports from 50 patients. Extracted data elements include demographical data, diagnosis, genetic marker, and procedure. The system achieves F-1 scores of around 95% for the majority of tests. Conclusions: Extracting data from pathology reports could enable more accurate knowledge to support biomedical research and clinical diagnosis. IDEAL-X provides a bridge that takes advantage of online machine learning based data extraction and the knowledge from human's feedback. By combining iterative online learning and adaptive controlled vocabularies, IDEAL-X can deliver highly adaptive and accurate data extraction to support patient search.

Background: Genomic medicine has the potential to improve care by tailoring treatments to the individual. There is consensus in the literature that pharmacogenomics (PGx) may be an ideal starting point for real-world implementation, due to the presence of well-characterized drug-gene interactions. Clinical Decision Support (CDS) is an ideal avenue by which to implement PGx at the bedside. Previous literature has established theoretical models for PGx CDS implementation and discussed a number of anticipated real-world challenges. However, work detailing actual PGx CDS implementation experiences has been limited. Anticipated challenges include data storage and management, system integration, physician acceptance, and more. Methods: In this study, we analyzed the experiences of ten members of the Electronic Medical Records and Genomics (eMERGE) Network, and one affiliate, in their attempts to implement PGx CDS. We examined the resulting PGx CDS system characteristics and conducted a survey to understand the unanticipated implementation challenges sites encountered. Results: Ten sites have successfully implemented at least one PGx CDS rule in the clinical setting. The majority of sites elected to create an Omic Ancillary System (OAS) to manage genetic and genomic data. All sites were able to adapt their existing CDS tools for PGx knowledge. The most common and impactful delays were not PGx-specific issues. Instead, they were general IT implementation problems, with top challenges including team coordination/communication and staffing. The challenges encountered caused a median total delay in system go-live of approximately two months. Conclusions: These results suggest that barriers to PGx CDS implementations are generally surmountable. Moreover, PGx CDS implementation may not be any more difficult than other healthcare IT projects of similar scope, as the most significant delays encountered were not unique to genomic medicine. These are encouraging results for any institution considering implementing a PGx CDS tool, and for the advancement of genomic medicine.

Introduction: Nucleolar changes in cancer cells are one of the cytologic features important to the tumor pathologist in cancer assessments of tissue biopsies. However, inter-observer variability and the manual approach to this work hamper the accuracy of the assessment by pathologists. In this paper, we propose a computational method for prominent nucleoli pattern detection. Materials and Methods: Thirty-five hematoxylin and eosin stained images were acquired from prostate cancer, breast cancer, renal clear cell cancer and renal papillary cell cancer tissues. Prostate cancer images were used for the development of a computer-based automated prominent nucleoli pattern detector built on a cascade farm. An ensemble of approximately 1000 cascades was constructed by permuting different combinations of classifiers such as support vector machines, eXclusive component analysis, boosting, and logistic regression. The output of cascades was then combined using the RankBoost algorithm. The output of our prominent nucleoli pattern detector is a ranked set of detected image patches of patterns of prominent nucleoli. Results: The mean number of detected prominent nucleoli patterns in the top 100 ranked detected objects was 58 in the prostate cancer dataset, 68 in the breast cancer dataset, 86 in the renal clear cell cancer dataset, and 76 in the renal papillary cell cancer dataset. The proposed cascade farm performs twice as good as the use of a single cascade proposed in the seminal paper by Viola and Jones. For comparison, a naive algorithm that randomly chooses a pixel as a nucleoli pattern would detect five correct patterns in the first 100 ranked objects. Conclusions: Detection of sparse nucleoli patterns in a large background of highly variable tissue patterns is a difficult challenge our method has overcome. This study developed an accurate prominent nucleoli pattern detector with the potential to be used in the clinical settings.

Background: Pathology reports typically require manual review to abstract research data. We developed a natural language processing (NLP) system to automatically interpret free-text breast pathology reports with limited assistance from manual abstraction. Methods: We used an iterative approach of machine learning algorithms and constructed groups of related findings to identify breast-related procedures and results from free-text pathology reports. We evaluated the NLP system using an all-or-nothing approach to determine which reports could be processed entirely using NLP and which reports needed manual review beyond NLP. We divided 3234 reports for development (2910, 90%), and evaluation (324, 10%) purposes using manually reviewed pathology data as our gold standard. Results: NLP correctly coded 12.7% of the evaluation set, flagged 49.1% of reports for manual review, incorrectly coded 30.8%, and correctly omitted 7.4% from the evaluation set due to irrelevancy (i.e. not breast-related). Common procedures and results were identified correctly (e.g. invasive ductal with 95.5% precision and 94.0% sensitivity), but entire reports were flagged for manual review because of rare findings and substantial variation in pathology report text. Conclusions: The NLP system we developed did not perform sufficiently for abstracting entire breast pathology reports. The all-or-nothing approach resulted in too broad of a scope of work and limited our flexibility to identify breast pathology procedures and results. Our NLP system was also limited by the lack of the gold standard data on rare findings and wide variation in pathology text. Focusing on individual, common elements and improving pathology text report standardization may improve performance.

Background: Mobile networks and smartphones are growing in developing countries. Expert telemedicine consultation will become more convenient and feasible. We wanted to report on our experience in using a smartphone and a 3-D printed adapter for capturing microscopic images. Methods: Images and videos from a gastrointestinal biopsy teaching set of referred cases from the AFIP were captured with an iPhone 5 smartphone fitted with a 3-D printed adapter. Nine pathologists worldwide evaluated the images for quality, adequacy for telepathology consultation, and confidence rendering a diagnosis based on the images viewed on the web. Results: Average Likert scales (ordinal data) for image quality (1=poor, 5=diagnostic) and adequacy for diagnosis (1=No, 5=Yes) had modes of 3 and 4, respectively. Adding a video overview of the specimen improved diagnostic confidence. The mode of confidence in diagnosis based on the images reviewed was four. In 31 instances, reviewers' diagnoses completely agreed with AFIP diagnosis, with partial agreement in 9 and major disagreement in 5. There was strong correlation between image quality and confidence (r = 0.78), image quality and adequacy of image (r = 0.73) and whether images were found adequate when reviewers were confident (r = 0.72). Intraclass Correlation for measuring reliability among the four reviewers who finished a majority of cases was high (quality=0.83, adequacy= 0.76 and confidence=0.92). Conclusions: Smartphones allow pathologists and other image dependent disciplines in low resource areas to transmit consultations to experts anywhere in the world. Improvements in camera resolution and training may mitigate some limitations found in this study.

Hematoxylin and eosin (H&E) staining is ubiquitous in pathology practice and research. As digital pathology has evolved, the reliance of quantitative methods that make use of H&E images has similarly expanded. For example, cell counting and nuclear morphometry rely on the accurate demarcation of nuclei from other structures and each other. One of the major obstacles to quantitative analysis of H&E images is the high degree of variability observed between different samples and different laboratories. In an effort to characterize this variability, as well as to provide a substrate that can potentially mitigate this factor in quantitative image analysis, we developed a technique to project H&E images into an optimized space more appropriate for many image analysis procedures. We used a decision tree-based support vector machine learning algorithm to classify 44 H&E stained whole slide images of resected breast tumors according to the histological structures that are present. This procedure takes an H&E image as an input and produces a classification map of the image that predicts the likelihood of a pixel belonging to any one of a set of user-defined structures (e.g., cytoplasm, stroma). By reducing these maps into their constituent pixels in color space, an optimal reference vector is obtained for each structure, which identifies the color attributes that maximally distinguish one structure from other elements in the image. We show that tissue structures can be identified using this semi-automated technique. By comparing structure centroids across different images, we obtained a quantitative depiction of H&E variability for each structure. This measurement can potentially be utilized in the laboratory to help calibrate daily staining or identify troublesome slides. Moreover, by aligning reference vectors derived from this technique, images can be transformed in a way that standardizes their color properties and makes them more amenable to image processing.

Background: Computerized physician order entry (CPOE) systems are quickly becoming ubiquitous, and groups of orders ("order sets") to allow for easy order input are a common feature. This provides a streamlined mechanism to view, modify, and place groups of related orders. This often serves as an electronic equivalent of a specialty requisition. A characteristic, of these order sets is that specific orders can be predetermined to be "preselected" or "defaulted-on" whenever the order set is used while others are "optional" or "defaulted-off" (though there is typically the option is to "deselect" defaulted-on tests in a given situation). While it seems intuitive that the defaults in an order set are often accepted, additional study is required to understand the impact of these "default" settings in an order set on ordering habits. This study set out to quantify the effect of changing the default settings of an order set. Methods: For quality improvement purposes, order sets dealing with transfusions were recently reviewed and modified to improve monitoring of outcome. Initially, the order for posttransfusion hematocrits and platelet count had the default setting changed from "optional" to "preselected." The default settings for platelet count was later changed back to "optional," allowing for a natural experiment to study the effect of the default selections of an order set on clinician ordering habits. Results: Posttransfusion hematocrit values were ordered for 8.3% of red cell transfusions when the default order set selection was "off" and for 57.4% of transfusions when the default selection was "preselected" (P < 0.0001). Posttransfusion platelet counts were ordered for 7.0% of platelet transfusions when the initial default order set selection was "optional," increased to 59.4% when the default was changed to "preselected" (P < 0.0001), and then decreased to 7.5% when the default selection was returned to "optional." The posttransfusion platelet count rates during the two "optional" periods: 7.0% versus 7.5% - were not statistically different (P = 0.620). Discussion: Default settings in CPOE order sets can significantly influence physician selection of laboratory tests. Careful consideration by all stakeholders, including clinicians and pathologists, should be obtained when establishing default settings in order sets.

Introduction: Histopathological images have rich structural information, are multi-channel in nature and contain meaningful pathological information at various scales. Sophisticated image analysis tools that can automatically extract discriminative information from the histopathology image slides for diagnosis remain an area of significant research activity. In this work, we focus on automated brain cancer grading, specifically glioma grading. Grading of a glioma is a highly important problem in pathology and is largely done manually by medical experts based on an examination of pathology slides (images). To complement the efforts of clinicians engaged in brain cancer diagnosis, we develop novel image processing algorithms and systems to automatically grade glioma tumor into two categories: Low-grade glioma (LGG) and high-grade glioma (HGG) which represent a more advanced stage of the disease. Results: We propose novel image processing algorithms based on spatial domain analysis for glioma tumor grading that will complement the clinical interpretation of the tissue. The image processing techniques are developed in close collaboration with medical experts to mimic the visual cues that a clinician looks for in judging of the grade of the disease. Specifically, two algorithmic techniques are developed: (1) A cell segmentation and cell-count profile creation for identification of Pseudopalisading Necrosis, and (2) a customized operation of spatial and morphological filters to accurately identify microvascular proliferation (MVP). In both techniques, a hierarchical decision is made via a decision tree mechanism. If either Pseudopalisading Necrosis or MVP is found present in any part of the histopathology slide, the whole slide is identified as HGG, which is consistent with World Health Organization guidelines. Experimental results on the Cancer Genome Atlas database are presented in the form of: (1) Successful detection rates of pseudopalisading necrosis and MVP regions, (2) overall classification accuracy into LGG and HGG categories, and (3) receiver operating characteristic curves which can facilitate a desirable trade-off between HGG detection and false-alarm rates. Conclusion: The proposed method demonstrates fairly high accuracy and compares favorably against best-known alternatives such as the state-of-the-art WND-CHARM feature set provided by NIH combined with powerful support vector machine classifier. Our results reveal that the proposed method can be beneficial to a clinician in effectively separating histopathology slides into LGG and HGG categories, particularly where the analysis of a large number of slides is needed. Our work also reveals that MVP regions are much harder to detect than Pseudopalisading Necrosis and increasing accuracy of automated image processing for MVP detection emerges as a significant future research direction.

Background: Little evidence is available concerning the impact of virtual microscopy (VM) in the undergraduate teaching of pathology. We aimed: (1) to determine the impact in student scores when moving from conventional microscopy (CM) to VM; (2) to assess the students' impressions and changes in study habits regarding the impact of this tool. Methods: We evaluated two groups taking the discipline of pathology in the same course, one using CM and the other VM. The same set of slides used in the CM classes was digitized in a VENTANA iScan HT (Roche Diagnostics, Sant Cugat, Spain) at ×20 and observed by the students using the Virtuoso viewer (Roche Diagnostics). We evaluated the skill level reached by the students with an online test. A voluntary survey was undertaken by the VM group to assess the students' impressions regarding the resource. The day and time of any accession to the viewer were registered. Results: There were no differences between the two groups in their marks in the online test (mean marks for the CM and the VM groups: 9.87 ± 0.34 and 9.86 ± 0.53, respectively; P = 0.880). 86.6% of the students found the software friendly, easy-to-use and effective. 71.6% of the students considered navigation easier with VM than with CM. The most appreciated feature of VM was the possibility to access the images anywhere and at any time (93.3%). 57.5% of the accesses were made on holidays and 41.9% later than 6:00 pm. Conclusions: Virtual microscopy can effectively replace the traditional methods of learning pathology, providing mobility and convenience to medical students.

Background: Whole slide imaging (WSI) is widely used for education and research, but is increasingly being used to streamline clinical workflow. We present our experience with regard to satisfaction and time utilization using oil immersion WSI for presentation of blood/marrow aspirate smears, core biopsies, and tissue sections in hematology/oncology tumor board/treatment planning conferences (TPC). Methods: Lymph nodes and bone marrow core biopsies were scanned at ×20 magnification and blood/marrow smears at 83X under oil immersion and uploaded to an online library with areas of interest to be displayed annotated digitally via web browser. Pathologist time required to prepare slides for scanning was compared to that required to prepare for microscope projection (MP). Time required to present cases during TPC was also compared. A 10-point evaluation survey was used to assess clinician satisfaction with each presentation method. Results: There was no significant difference in hematopathologist preparation time between WSI and MP. However, presentation time was significantly less for WSI compared to MP as selection and annotation of slides was done prior to TPC with WSI, enabling more efficient use of TPC presentation time. Survey results showed a significant increase in satisfaction by clinical attendees with regard to image quality, efficiency of presentation of pertinent findings, aid in clinical decision-making, and overall satisfaction regarding pathology presentation. A majority of respondents also noted decreased motion sickness with WSI. Conclusions: Whole slide imaging, particularly with the ability to use oil scanning, provides higher quality images compared to MP and significantly increases clinician satisfaction. WSI streamlines preparation for TPC by permitting prior slide selection, resulting in greater efficiency during TPC presentation.

Context: Distinction of spindle cell melanoma (SM) and desmoplastic melanoma (DM) is clinically important due to differences in metastatic rate and prognosis; however, histological distinction is not always straightforward. During a routine review of cases, we noted differences in nuclear circularity between SM and DM. Aim: The primary aim in our study was to determine whether these differences in nuclear circularity, when assessed using a basic ImageJ-based threshold extraction, can serve as a diagnostic classifier to distinguish DM from SM. Settings and Design: Our retrospective analysis of an established patient cohort (SM n = 9, DM n = 9) was employed to determine discriminatory power. Subjects and Methods: Regions of interest (total n = 108; 6 images per case) were selected from scanned H and E-stained histological sections, and nuclear circularity was extracted and quantified by computational image analysis using open source tools (plugins for ImageJ). Statistical Analysis: Using analysis of variance, t-tests, and Fisher's exact tests, we compared extracted quantitative shape measures; statistical significance was defined as P < 0.05. Results: Classifying circularity values into four shape categories (spindled, elongated, oval, round) demonstrated significant differences in the spindled and round categories. Paradoxically, DM contained more spindled nuclei than SM (P = 0.011) and SM contained more round nuclei than DM (P = 0.026). Performance assessment using a combined shape-classification of the round and spindled fractions showed 88.9% accuracy and a Youden index of 0.77. Conclusions: Spindle cell melanoma and DM differ significantly in their nuclear morphology with respect to fractions of round and spindled nuclei. Our study demonstrates that quantifying nuclear circularity can be used as an adjunct diagnostic tool for distinction of DM and SM.

Background: Effective blood inventory management reduces outdates of blood products. Multiple strategies have been employed to reduce the rate of red blood cell (RBC) unit outdate. We designed an automated real-time web-based dashboard interfaced with our laboratory information system to effectively recycle red cell units. The objective of our approach is to decrease RBC outdate rates within our transfusion service. Methods: The dashboard was deployed in August 2011 and is accessed by a shortcut that was placed on the desktops of all blood transfusion services computers in the Capital District Health Authority region. It was designed to refresh automatically every 10 min. The dashboard provides all vital information on RBC units, and implemented a color coding scheme to indicate an RBC unit's proximity to expiration. Results: The overall RBC unit outdate rate in the 7 months period following implementation of the dashboard (September 2011-March 2012) was 1.24% (123 units outdated/9763 units received), compared to similar periods in 2010-2011 and 2009-2010: 2.03% (188/9395) and 2.81% (261/9220), respectively. The odds ratio of a RBC unit outdate postdashboard (2011-2012) compared with 2010-2011 was 0.625 (95% confidence interval: 0.497-0.786; P < 0.0001). Conclusion: Our dashboard system is an inexpensive and novel blood inventory management system which was associated with a significant reduction in RBC unit outdate rates at our institution over a period of 7 months. This system, or components of it, could be a useful addition to existing RBC management systems at other institutions.

Context: General and subject specific practice examinations for students in health sciences studying pathology were placed onto a free public internet web site entitled web path and were accessed four clicks from the home web site menu. Subjects and Methods: Multiple choice questions were coded into. html files with JavaScript functions for web browser viewing in a timed format. A Perl programming language script with common gateway interface for web page forms scored examinations and placed results into a log file on an internet computer server. The four general review examinations of 30 questions each could be completed in up to 30 min. The 17 subject specific examinations of 10 questions each with accompanying images could be completed in up to 15 min each. The results of scores and user educational field of study from log files were compiled from June 2006 to January 2014. Results: The four general review examinations had 31,639 accesses with completion of all questions, for a completion rate of 54% and average score of 75%. A score of 100% was achieved by 7% of users, ≥90% by 21%, and ≥50% score by 95% of users. In top to bottom web page menu order, review examination usage was 44%, 24%, 17%, and 15% of all accessions. The 17 subject specific examinations had 103,028 completions, with completion rate 73% and average score 74%. Scoring at 100% was 20% overall, ≥90% by 37%, and ≥50% score by 90% of users. The first three menu items on the web page accounted for 12.6%, 10.0%, and 8.2% of all completions, and the bottom three accounted for no more than 2.2% each. Conclusions: Completion rates were higher for shorter 10 questions subject examinations. Users identifying themselves as MD/DO scored higher than other users, averaging 75%. Usage was higher for examinations at the top of the web page menu. Scores achieved suggest that a cohort of serious users fully completing the examinations had sufficient preparation to use them to support their pathology education.

Background: Digital pathology offers potential improvements in workflow and interpretive accuracy. Although currently digital pathology is commonly used for research and education, its clinical use has been limited to niche applications such as frozen sections and remote second opinion consultations. This is mainly due to regulatory hurdles, but also to a dearth of data supporting a positive economic cost-benefit. Large scale adoption of digital pathology and the integration of digital slides into the routine anatomic/surgical pathology "slide less" clinical workflow will occur only if digital pathology will offer a quantifiable benefit, which could come in the form of more efficient and/or higher quality care. Aim: As a large academic-based health care organization expecting to adopt digital pathology for primary diagnosis upon its regulatory approval, our institution estimated potential operational cost savings offered by the implementation of an enterprise-wide digital pathology system (DPS). Methods: Projected cost savings were calculated for the first 5 years following implementation of a DPS based on operational data collected from the pathology department. Projected savings were based on two factors: (1) Productivity and lab consolidation savings; and (2) avoided treatment costs due to improvements in the accuracy of cancer diagnoses among nonsubspecialty pathologists. Detailed analyses of incremental treatment costs due to interpretive errors, resulting in either a false positive or false negative diagnosis, was performed for melanoma and breast cancer and extrapolated to 10 other common cancers. Results: When phased in over 5-years, total cost savings based on anticipated improvements in pathology productivity and histology lab consolidation were estimated at $12.4 million for an institution with 219,000 annual accessions. The main contributing factors to these savings were gains in pathologist clinical full-time equivalent capacity impacted by improved pathologist productivity and workload distribution. Expanding the current localized specialty sign-out model to an enterprise-wide shared general/subspecialist sign-out model could potentially reduce costs of incorrect treatment by $5.4 million. These calculations were based on annual over and under treatment costs for breast cancer and melanoma estimated to be approximately $26,000 and $11,000/case, respectively, and extrapolated to $21,500/case for other cancer types. Conclusions: The projected 5-year total cost savings for our large academic-based health care organization upon fully implementing a DPS was approximately $18 million. If the costs of digital pathology acquisition and implementation do not exceed this value, the return on investment becomes attractive to hospital administrators. Furthermore, improved patient outcome enabled by this technology strengthens the argument supporting adoption of an enterprise-wide DPS.

Background: Mortality in cancer patients is directly attributable to the ability of cancer cells to metastasize to distant sites from the primary tumor. This migration of tumor cells begins with a remodeling of the local tumor microenvironment, including changes to the extracellular matrix and the recruitment of stromal cells, both of which facilitate invasion of tumor cells into the bloodstream. In breast cancer, it has been proposed that the alignment of collagen fibers surrounding tumor epithelial cells can serve as a quantitative image-based biomarker for survival of invasive ductal carcinoma patients. Specific types of collagen alignment have been identified for their prognostic value and now these tumor associated collagen signatures (TACS) are central to several clinical specimen imaging trials. Here, we implement the semi-automated acquisition and analysis of this TACS candidate biomarker and demonstrate a protocol that will allow consistent scoring to be performed throughout large patient cohorts. Methods: Using large field of view high resolution microscopy techniques, image processing and supervised learning methods, we are able to quantify and score features of collagen fiber alignment with respect to adjacent tumor-stromal boundaries. Results: Our semi-automated technique produced scores that have statistically significant correlation with scores generated by a panel of three human observers. In addition, our system generated classification scores that accurately predicted survival in a cohort of 196 breast cancer patients. Feature rank analysis reveals that TACS positive fibers are more well-aligned with each other, are of generally lower density, and terminate within or near groups of epithelial cells at larger angles of interaction. Conclusion: These results demonstrate the utility of a supervised learning protocol for streamlining the analysis of collagen alignment with respect to tumor stromal boundaries.

Introduction: Recent technology developments have demonstrated the benefit of using whole slide imaging (WSI) in computer-aided diagnosis. In this paper, we explore the feasibility of using automatic WSI analysis to assist grading of clear cell renal cell carcinoma (RCC), which is a manual task traditionally performed by pathologists. Materials and Methods: Automatic WSI analysis was applied to 39 hematoxylin and eosin-stained digitized slides of clear cell RCC with varying grades. Kernel regression was used to estimate the spatial distribution of nuclear size across the entire slides. The analysis results were correlated with Fuhrman nuclear grades determined by pathologists. Results: The spatial distribution of nuclear size provided a panoramic view of the tissue sections. The distribution images facilitated locating regions of interest, such as high-grade regions and areas with necrosis. The statistical analysis showed that the maximum nuclear size was significantly different (P < 0.001) between low-grade (Grades I and II) and high-grade tumors (Grades III and IV). The receiver operating characteristics analysis showed that the maximum nuclear size distinguished high-grade and low-grade tumors with a false positive rate of 0.2 and a true positive rate of 1.0. The area under the curve is 0.97. Conclusion: The automatic WSI analysis allows pathologists to see the spatial distribution of nuclei size inside the tumors. The maximum nuclear size can also be used to differentiate low-grade and high-grade clear cell RCC with good sensitivity and specificity. These data suggest that automatic WSI analysis may facilitate pathologic grading of renal tumors and reduce variability encountered with manual grading.

We propose a methodology for the design of features mimicking the visual cues used by pathologists when identifying tissues in hematoxylin and eosin (H&E)-stained samples. Background: H&E staining is the gold standard in clinical histology; it is cheap and universally used, producing a vast number of histopathological samples. While pathologists accurately and consistently identify tissues and their pathologies, it is a time-consuming and expensive task, establishing the need for automated algorithms for improved throughput and robustness. Methods: We use an iterative feedback process to design a histopathology vocabulary (HV), a concise set of features that mimic the visual cues used by pathologists, e.g. "cytoplasm color" or "nucleus density." These features are based in histology and understood by both pathologists and engineers. We compare our HV to several generic texture-feature sets in a pixel-level classification algorithm. Results: Results on delineating and identifying tissues in teratoma tumor samples validate our expert knowledge-based approach. Conclusions: The HV can be an effective tool for identifying and delineating teratoma components from images of H&E-stained tissue samples.

Introduction: Digital pathology is a relatively new field. Inventors of technology in this field typically file for patents to protect their intellectual property. An understanding of the patent landscape is crucial for companies wishing to secure patent protection and market dominance for their products. To our knowledge, there has been no prior systematic review of patents related to digital pathology. Therefore, the aim of this study was to systematically identify and evaluate United States patents and patent applications related to digital pathology. Materials and Methods: Issued patents and patent applications related to digital pathology published in the United States Patent and Trademark Office (USPTO) database (www.uspto.gov) (through January 2014) were searched using the Google Patents search engine (Google Inc., Mountain View, California, USA). Keywords and phrases related to digital pathology, whole-slide imaging (WSI), image analysis, and telepathology were used to query the USPTO database. Data were downloaded and analyzed using the Papers application (Mekentosj BV, Aalsmeer, Netherlands). Results: A total of 588 United States patents that pertain to digital pathology were identified. In addition, 228 patent applications were identified, including 155 that were pending, 65 abandoned, and eight rejected. Of the 588 patents granted, 348 (59.18%) were specific to pathology, while 240 (40.82%) included more general patents also usable outside of pathology. There were 70 (21.12%) patents specific to pathology and 57 (23.75%) more general patents that had expired. Over 120 unique entities (individual inventors, academic institutions, and private companies) applied for pathology specific patents. Patents dealt largely with telepathology and image analysis. WSI related patents addressed image acquisition (scanning and focus), quality (z-stacks), management (storage, retrieval, and transmission of WSI files), and viewing (graphical user interface (GUI), workflow, slide navigation and remote control). An increasing number of recent patents focused on computer-aided diagnosis (CAD) and digital consultation networks. Conclusion: In the last 2 decades, there have been an increasing number of patents granted and patent applications filed related to digital pathology. The number of these patents quadrupled during the last decade, and this trend is predicted to intensify based on the number of patent applications already published by the USPTO.

Background: Autoverification is a process of using computer-based rules to verify clinical laboratory test results without manual intervention. To date, there is little published data on the use of autoverification over the course of years in a clinical laboratory. We describe the evolution and application of autoverification in an academic medical center clinical chemistry core laboratory. Subjects and Methods: At the institution of the study, autoverification developed from rudimentary rules in the laboratory information system (LIS) to extensive and sophisticated rules mostly in middleware software. Rules incorporated decisions based on instrument error flags, interference indices, analytical measurement ranges (AMRs), delta checks, dilution protocols, results suggestive of compromised or contaminated specimens, and 'absurd' (physiologically improbable) values. Results: The autoverification rate for tests performed in the core clinical chemistry laboratory has increased over the course of 13 years from 40% to the current overall rate of 99.5%. A high percentage of critical values now autoverify. The highest rates of autoverification occurred with the most frequently ordered tests such as the basic metabolic panel (sodium, potassium, chloride, carbon dioxide, creatinine, blood urea nitrogen, calcium, glucose; 99.6%), albumin (99.8%), and alanine aminotransferase (99.7%). The lowest rates of autoverification occurred with some therapeutic drug levels (gentamicin, lithium, and methotrexate) and with serum free light chains (kappa/lambda), mostly due to need for offline dilution and manual filing of results. Rules also caught very rare occurrences such as plasma albumin exceeding total protein (usually indicative of an error such as short sample or bubble that evaded detection) and marked discrepancy between total bilirubin and the spectrophotometric icteric index (usually due to interference of the bilirubin assay by immunoglobulin (Ig) M monoclonal gammopathy). Conclusions: Our results suggest that a high rate of autoverification is possible with modern clinical chemistry analyzers. The ability to autoverify a high percentage of results increases productivity and allows clinical laboratory staff to focus attention on the small number of specimens and results that require manual review and investigation.

Background: Color consistency in histology images is still an issue in digital pathology. Different imaging systems reproduced the colors of a histological slide differently. Materials and Methods: Color correction was implemented using the color information of the nine color patches of a color calibration slide. The inherent spectral colors of these patches along with their scanned colors were used to derive a color correction matrix whose coefficients were used to convert the pixels' colors to their target colors. Results: There was a significant reduction in the CIELAB color difference, between images of the same H & E histological slide produced by two different whole slide scanners by 3.42 units, P < 0.001 at 95% confidence level. Conclusion: Color variations in histological images brought about by whole slide scanning can be effectively normalized with the use of the color calibration slide.

Background: Whole slide imaging (WSI) offers a novel approach to digitize and review pathology slides, but the voluminous data generated by this technology demand new computational methods for image analysis. Materials and Methods: In this study, we report a method that recognizes stains in WSI data and uses kernel density estimator to calculate the stain density across the digitized pathology slides. The validation study was conducted using a rat model of acute cardiac allograft rejection and another rat model of heart ischemia/reperfusion injury. Immunohistochemistry (IHC) was conducted to label ED1 ⁺ macrophages in the tissue sections and the stained slides were digitized by a whole slide scanner. The whole slide images were tessellated to enable parallel processing. Pixel-wise stain classification was conducted to classify the IHC stains from those of the background and the density distribution of the identified IHC stains was then calculated by the kernel density estimator. Results: The regression analysis showed a correlation coefficient of 0.8961 between the number of IHC stains counted by our stain recognition algorithm and that by the manual counting, suggesting that our stain recognition algorithm was in good agreement with the manual counting. The density distribution of the IHC stains showed a consistent pattern with those of the cellular magnetic resonance (MR) images that detected macrophages labeled by ultrasmall superparamagnetic iron-oxide or micron-sized iron-oxide particles. Conclusions: Our method provides a new imaging modality to facilitate clinical diagnosis. It also provides a way to validate/correlate cellular MRI data used for tracking immune-cell infiltration in cardiac transplant rejection and cardiac ischemic injury.

Background: The use of virtual microscopy (VM) in clinical cytology has been limited due to the inability to focus through three dimensional (3D) cell clusters with a single focal plane (2D images). Limited information exists regarding the optimal scanning parameters for 3D scanning. Aims: The purpose of this study was to determine the optimal number of the focal plane levels and the optimal scanning interval to digitize gynecological (GYN) specimens prepared on SurePath^™ glass slides while maintaining a manageable file size. Subjects and Methods: The iScanCoreo Au scanner (Ventana, AZ, USA) was used to digitize 192 SurePath^™ glass slides at three focal plane levels at 1 μ interval. The digitized virtual images (VI) were annotated using BioImagene's Image Viewer. Five participants interpreted the VI and recorded the focal plane level at which they felt confident and later interpreted the corresponding glass slide specimens using light microscopy (LM). The participants completed a survey about their experiences. Inter-rater agreement and concordance between the VI and the glass slide specimens were evaluated. Results: This study determined an overall high intra-rater diagnostic concordance between glass and VI (89-97%), however, the inter-rater agreement for all cases was higher for LM (94%) compared with VM (82%). Survey results indicate participants found low grade dysplasia and koilocytes easy to diagnose using three focal plane levels, the image enhancement tool was useful and focusing through the cells helped with interpretation; however, the participants found VI with hyperchromatic crowded groups challenging to interpret. Participants reported they prefer using LM over VM. This study supports using three focal plane levels and 1 μ interval to expand the use of VM in GYN cytology. Conclusion: Future improvements in technology and appropriate training should make this format a more preferable and practical option in clinical cytology.

Background: Oral submucous fibrosis (OSF) is a pre-cancerous condition with features of chronic, inflammatory and progressive sub-epithelial fibrotic disorder of the buccal mucosa. In this study, malignant potentiality of OSF has been assessed by quantification of immunohistochemical expression of epithelial prime regulator-p63 molecule in correlation to its malignant (oral squamous cell carcinoma [OSCC] and normal counterpart [normal oral mucosa [NOM]). Attributes of spatial extent and distribution of p63 ⁺ expression in the epithelium have been investigated. Further, a correlated assessment of histopathological attributes inferred from H&E staining and their mathematical counterparts (molecular pathology of p63) have been proposed. The suggested analytical framework envisaged standardization of the immunohistochemistry evaluation procedure for the molecular marker, using computer-aided image analysis, toward enhancing its prognostic value. Subjects and Methods: In histopathologically confirmed OSF, OSCC and NOM tissue sections, p63 ⁺ nuclei were localized and segmented by identifying regional maxima in plateau-like intensity spatial profiles of nuclei. The clustered nuclei were localized and segmented by identifying concave points in the morphometry and by marker-controlled watersheds. Voronoi tessellations were constructed around nuclei centroids and mean values of spatial-relation metrics such as tessellation area, tessellation perimeter, roundness factor and disorder of the area were extracted. Morphology and extent of expression are characterized by area, diameter, perimeter, compactness, eccentricity and density, fraction of p63 ⁺ expression and expression distance of p63 ⁺ nuclei. Results: Correlative framework between histopathological features characterizing malignant potentiality and their quantitative p63 counterparts was developed. Statistical analyses of mathematical trends were evaluated between different biologically relevant combinations: (i) NOM to oral submucous fibrosis without dysplasia (OSFWT) (ii) NOM to oral submucous fibrosis with dysplasia (OSFWD) (iii) OSFWT-OSFWD (iv) OSFWD-OSCC. Significant histopathogical correlates and their corroborative mathematical features, inferred from p63 staining, were also investigated into. Conclusion: Quantitative assessment and correlative analysis identified mathematical features related to hyperplasia, cellular stratification, differentiation and maturation, shape and size, nuclear crowding and nucleocytoplasmic ratio. It is envisaged that this approach for analyzing the p63 expression and its distribution pattern may help to establish it as a quantitative bio-marker to predict the malignant potentiality and progression. The proposed work would be a value addition to the gold standard by incorporating an observer-independent framework for the associated molecular pathology.

Background: Advances in digital pathology are accelerating integration of this technology into anatomic pathology (AP). To optimize implementation and adoption of digital pathology systems within a large healthcare organization, initial assessment of both end user (pathologist) needs and organizational infrastructure are required. Contextual inquiry is a qualitative, user-centered tool for collecting, interpreting, and aggregating such detailed data about work practices that can be employed to help identify specific needs and requirements. Aim: Using contextual inquiry, the objective of this study was to identify the unique work practices and requirements in AP for the United States (US) Air Force Medical Service (AFMS) that had to be targeted in order to support their transition to digital pathology. Subjects and Methods: A pathology-centered observer team conducted 1.5 h interviews with a total of 24 AFMS pathologists and histology lab personnel at three large regional centers and one smaller peripheral AFMS pathology center using contextual inquiry guidelines. Findings were documented as notes and arranged into a hierarchal organization of common themes based on user-provided data, defined as an affinity diagram. These data were also organized into consolidated graphic models that characterized AFMS pathology work practices, structure, and requirements. Results: Over 1,200 recorded notes were grouped into an affinity diagram composed of 27 third-level, 10 second-level, and five main-level (workflow and workload distribution, quality, communication, military culture, and technology) categories. When combined with workflow and cultural models, the findings revealed that AFMS pathologists had needs that were unique to their military setting, when compared to civilian pathologists. These unique needs included having to serve a globally distributed patient population, transient staff, but a uniform information technology (IT) structure. Conclusions: The contextual inquiry method helped reveal similarities and key differences with civilian pathologists. Such an analysis helped identify specific instances that would benefit from implementing digital pathology in a military environment. Employing digital pathology to facilitate workload distribution, secondary consultations, and quality assurance (over-reads) could help the AFMS deliver more accurate, efficient, and timely AP services at a global level.

Background: In general, surgical pathology reviews report protein expression by tumors in a semi-quantitative manner, that is, -, -/+, +/-, +. At the same time, the experimental pathology literature provides multiple examples of precise expression levels determined by immunohistochemical (IHC) tissue examination of populations of tumors. Natural language processing (NLP) techniques enable the automated extraction of such information through text mining. We propose establishing a database linking quantitative protein expression levels with specific tumor classifications through NLP. Materials and Methods: Our method takes advantage of typical forms of representing experimental findings in terms of percentages of protein expression manifest by the tumor population under study. Characteristically, percentages are represented straightforwardly with the % symbol or as the number of positive findings of the total population. Such text is readily recognized using regular expressions and templates permitting extraction of sentences containing these forms for further analysis using grammatical structures and rule-based algorithms. Results: Our pilot study is limited to the extraction of such information related to lymphomas. We achieved a satisfactory level of retrieval as reflected in scores of 69.91% precision and 57.25% recall with an F-score of 62.95%. In addition, we demonstrate the utility of a web-based curation tool for confirming and correcting our findings. Conclusions: The experimental pathology literature represents a rich source of pathobiological information, which has been relatively underutilized. There has been a combinatorial explosion of knowledge within the pathology domain as represented by increasing numbers of immunophenotypes and disease subclassifications. NLP techniques support practical text mining techniques for extracting this knowledge and organizing it in forms appropriate for pathology decision support systems.

Background: Leukocyte differentials are an important component of clinical care. Morphologic assessment of peripheral blood smears (PBS) may be required to accurately classify leukocytes. However, manual microscopy is labor intensive. The CellaVision DM96 is an automated system that acquires digital images of leukocytes on PBS, pre-classifies the cell type, and displays them on screen for a Technologist or Pathologist to approve or reclassify. Our study compares the results of the DM96 with manual microscopy. Methods: Three hundred and fifty-nine PBS were selected and assessed by manual microscopy with a 200 leukocyte cell count. They were then reassessed using the CellaVision DM96 with a 115 leukocyte cell count including reclassification when necessary. Correlation between the manual microscopy results and the CellaVision DM96 results was calculated for each cell type. Results: The correlation coefficients (r² ) range from a high of 0.99 for blasts to a low of 0.72 for metamyelocytes. Conclusions: The correlation between the CellaVision DM96 and manual microscopy was as good or better than the previously published data. The accuracy of leukocyte classification depended on the cell type, and in general, there was lower correlation for rare cell types. However, the correlation is similar to previous studies on the correlation of manual microscopy with an established reference result. Therefore, the CellaVision DM96 is appropriate for clinical implementation.

Background: Algorithm evaluation provides a means to characterize variability across image analysis algorithms, validate algorithms by comparison with human annotations, combine results from multiple algorithms for performance improvement, and facilitate algorithm sensitivity studies. The sizes of images and image analysis results in pathology image analysis pose significant challenges in algorithm evaluation. We present an efficient parallel spatial database approach to model, normalize, manage, and query large volumes of analytical image result data. This provides an efficient platform for algorithm evaluation. Our experiments with a set of brain tumor images demonstrate the application, scalability, and effectiveness of the platform. Context: The paper describes an approach and platform for evaluation of pathology image analysis algorithms. The platform facilitates algorithm evaluation through a high-performance database built on the Pathology Analytic Imaging Standards (PAIS) data model. Aims: (1) Develop a framework to support algorithm evaluation by modeling and managing analytical results and human annotations from pathology images; (2) Create a robust data normalization tool for converting, validating, and fixing spatial data from algorithm or human annotations; (3) Develop a set of queries to support data sampling and result comparisons; (4) Achieve high performance computation capacity via a parallel data management infrastructure, parallel data loading and spatial indexing optimizations in this infrastructure. Materials and Methods: We have considered two scenarios for algorithm evaluation: (1) algorithm comparison where multiple result sets from different methods are compared and consolidated; and (2) algorithm validation where algorithm results are compared with human annotations. We have developed a spatial normalization toolkit to validate and normalize spatial boundaries produced by image analysis algorithms or human annotations. The validated data were formatted based on the PAIS data model and loaded into a spatial database. To support efficient data loading, we have implemented a parallel data loading tool that takes advantage of multi-core CPUs to accelerate data injection. The spatial database manages both geometric shapes and image features or classifications, and enables spatial sampling, result comparison, and result aggregation through expressive structured query language (SQL) queries with spatial extensions. To provide scalable and efficient query support, we have employed a shared nothing parallel database architecture, which distributes data homogenously across multiple database partitions to take advantage of parallel computation power and implements spatial indexing to achieve high I/O throughput. Results: Our work proposes a high performance, parallel spatial database platform for algorithm validation and comparison. This platform was evaluated by storing, managing, and comparing analysis results from a set of brain tumor whole slide images. The tools we develop are open source and available to download. Conclusions: Pathology image algorithm validation and comparison are essential to iterative algorithm development and refinement. One critical component is the support for queries involving spatial predicates and comparisons. In our work, we develop an efficient data model and parallel database approach to model, normalize, manage and query large volumes of analytical image result data. Our experiments demonstrate that the data partitioning strategy and the grid-based indexing result in good data distribution across database nodes and reduce I/O overhead in spatial join queries through parallel retrieval of relevant data and quick subsetting of datasets. The set of tools in the framework provide a full pipeline to normalize, load, manage and query analytical results for algorithm evaluation.

Digital pathology is a rapidly evolving niche in the world of pathology and is likely to increase in popularity as technology improves. We performed a questionnaire for pathologists and pathology residents across Canada, in order to determine their current experiences and attitudes towards digital pathology; which modalities digital pathology is best suited for; and to assess the need for training in digital pathology amongst pathology residents and staff. An online survey consisting of 24 yes/no, multiple choice and free text questions regarding digital pathology was sent out via E-mail to all members of the Canadian Association of Pathologists and pathology residents across Canada. Survey results showed that telepathology (TP) is used in approximately 43% of institutions, primarily for teaching purposes (65%), followed by operating room consults (46%). Seventy-one percent of respondents believe there is a need for TP in their practice; 85% use digital images in their practice. The top two favored applications for digital pathology are teaching and consultation services, with the main advantage being easier access to cases. The main limitations of using digital pathology are cost and image/diagnostic quality. Sixty-two percent of respondents would attend training courses in pathology informatics and 91% think informatics should be part of residency training. The results of the survey indicate that Pathologists and residents across Canada do see a need for TP and the use of digital images in their daily practice. Integration of an informatics component into resident training programs and courses for staff Pathologists would be welcomed.

Context: Digital pathology has the potential to dramatically alter the way pathologists work, yet little is known about pathologists' viewing behavior while interpreting digital whole slide images. While tracking pathologist eye movements when viewing digital slides may be the most direct method of capturing pathologists' viewing strategies, this technique is cumbersome and technically challenging to use in remote settings. Tracking pathologist mouse cursor movements may serve as a practical method of studying digital slide interpretation, and mouse cursor data may illuminate pathologists' viewing strategies and time expenditures in their interpretive workflow. Aims: To evaluate the utility of mouse cursor movement data, in addition to eye-tracking data, in studying pathologists' attention and viewing behavior. Settings and Design: Pathologists (N = 7) viewed 10 digital whole slide images of breast tissue that were selected using a random stratified sampling technique to include a range of breast pathology diagnoses (benign/atypia, carcinoma in situ, and invasive breast cancer). A panel of three expert breast pathologists established a consensus diagnosis for each case using a modified Delphi approach. Materials and Methods: Participants' foveal vision was tracked using SensoMotoric Instruments RED 60 Hz eye-tracking system. Mouse cursor movement was tracked using a custom MATLAB script. Statistical Analysis Used: Data on eye-gaze and mouse cursor position were gathered at fixed intervals and analyzed using distance comparisons and regression analyses by slide diagnosis and pathologist expertise. Pathologists' accuracy (defined as percent agreement with the expert consensus diagnoses) and efficiency (accuracy and speed) were also analyzed. Results: Mean viewing time per slide was 75.2 seconds (SD = 38.42). Accuracy (percent agreement with expert consensus) by diagnosis type was: 83% (benign/atypia); 48% (carcinoma in situ); and 93% (invasive). Spatial coupling was close between eye-gaze and mouse cursor positions (highest frequency ∆x was 4.00px (SD = 16.10), and ∆y was 37.50px (SD = 28.08)). Mouse cursor position moderately predicted eye gaze patterns (Rx = 0.33 and Ry = 0.21). Conclusions: Data detailing mouse cursor movements may be a useful addition to future studies of pathologists' accuracy and efficiency when using digital pathology.

Background: In the recent years, the advances in digital methods in pathology have resulted in the use of telecytology in the immediate assessment of fine needle aspiration (FNA) specimens. However, there is a need for organ-based and body site-specific studies on the use of telecytology for the immediate assessment of FNA to evaluate its pitfalls and limitations. We present our experience with the use of telecytology for on-site evaluation of ultrasound-guided FNA (USG-FNA) of axillary lymph nodes in a remote breast care center. Materials and Methods: Real-time images of Diff-Quik-stained cytology smears were obtained with an Olympus digital camera attached to an Olympus CX41 microscope and transmitted via ethernet by a cytotechnologist to a pathologist who rendered preliminary diagnosis while communicating with the on-site cytotechnologist over the Vocera system. The accuracy of the preliminary diagnosis was compared with the final diagnosis, retrospectively. Results: A total of 39 female patients (mean age: 50.5 years) seen at the breast care center underwent USG-FNA of 44 axillary nodes. Preliminary diagnoses of benign, suspicious/malignant, and unsatisfactory were 41, 52, and 7%, respectively. Only one of the 23 cases that were initially interpreted as benign was reclassified as suspicious on final cytologic diagnosis. Seventeen of 18 suspicious/malignant cases on initial cytology corresponded with a malignant diagnosis on final cytology. One suspicious case was reclassified as benign on final cytologic diagnosis. All unsatisfactory cases remained inadequate for final cytologic interpretation. The presence of additional material in the cell block and interpretative error were the main reasons for discrepancy, accounting for the two discrepant cases. Conclusions: This retrospective study demonstrates that the on-site telecytology evaluation of USG-FNA of axillary lymph nodes in patients at a remote breast care center was highly accurate compared with the final cytologic evaluation. It allows pathologists to use their time more efficiently and makes on-site evaluation at a remote site possible.

Background: For decades anatomic pathology (AP) workflow have been a highly manual process based on the use of an optical microscope and glass slides. Recent innovations in scanning and digitizing of entire glass slides are accelerating a move toward widespread adoption and implementation of a workflow based on digital slides and their supporting information management software. To support the design of digital pathology systems and ensure their adoption into pathology practice, the needs of the main users within the AP workflow, the pathologists, should be identified. Contextual inquiry is a qualitative, user-centered, social method designed to identify and understand users' needs and is utilized for collecting, interpreting, and aggregating in-detail aspects of work. Objective: Contextual inquiry was utilized to document current AP workflow, identify processes that may benefit from the introduction of digital pathology systems, and establish design requirements for digital pathology systems that will meet pathologists' needs. Materials and Methods: Pathologists were observed and interviewed at a large academic medical center according to contextual inquiry guidelines established by Holtzblatt et al. 1998. Notes representing user-provided data were documented during observation sessions. An affinity diagram, a hierarchal organization of the notes based on common themes in the data, was created. Five graphical models were developed to help visualize the data including sequence, flow, artifact, physical, and cultural models. Results: A total of six pathologists were observed by a team of two researchers. A total of 254 affinity notes were documented and organized using a system based on topical hierarchy, including 75 third-level, 24 second-level, and five main-level categories, including technology, communication, synthesis/preparation, organization, and workflow. Current AP workflow was labor intensive and lacked scalability. A large number of processes that may possibly improve following the introduction of digital pathology systems were identified. These work processes included case management, case examination and review, and final case reporting. Furthermore, a digital slide system should integrate with the anatomic pathologic laboratory information system. Conclusions: To our knowledge, this is the first study that utilized the contextual inquiry method to document AP workflow. Findings were used to establish key requirements for the design of digital pathology systems.

The robustness of image features is a very important consideration in quantitative image analysis. The objective of this paper is to investigate the robustness of a range of image texture features using hematoxylin stained breast tissue microarray slides which are assessed while simulating different imaging challenges including out of focus, changes in magnification and variations in illumination, noise, compression, distortion, and rotation. We employed five texture analysis methods and tested them while introducing all of the challenges listed above. The texture features that were evaluated include co-occurrence matrix, center-symmetric auto-correlation, texture feature coding method, local binary pattern, and texton. Due to the independence of each transformation and texture descriptor, a network structured combination was proposed and deployed on the Rutgers private cloud. The experiments utilized 20 randomly selected tissue microarray cores. All the combinations of the image transformations and deformations are calculated, and the whole feature extraction procedure was completed in 70 minutes using a cloud equipped with 20 nodes. Center-symmetric auto-correlation outperforms all the other four texture descriptors but also requires the longest computational time. It is roughly 10 times slower than local binary pattern and texton. From a speed perspective, both the local binary pattern and texton features provided excellent performance for classification and content-based image retrieval.

Background: Graphical reports that contain charts, images, and tables have potential to convey information more effectively than text-based reports; however, studies have not measured how much clinicians value such features. We sought to identify factors that might influence the utilization of reports with graphical elements postulating that this is a surrogate for relative clinical utility of these graphical elements. Materials and Methods: We implemented a pilot project at ARUP laboratories to develop online enhanced laboratory test reports that contained graphical elements. We monitored on-demand clinician access to reports generated for 48 reportable tests over 22 months. We evaluated utilization of reports with graphical elements by clinicians at all institutions that use ARUP as a reference laboratory using descriptive statistics, regression, and meta-analysis tools to evaluate groups of similar test reports. Results: Median download rate by test was 8.6% with high heterogeneity in download rates between tests. Test reports with additional graphical elements were not necessarily downloaded more often than reports without these elements. Recently implemented tests and tests reporting abnormal results were associated with higher download rates (P < 0.01). Higher volume tests were associated with lower download rates (P = 0.03). Conclusions: In select cases graphical information may be clinically useful, particularly for less frequently ordered tests and in on reports of abnormal results. The utilization data presented could be used as a reference point for other laboratories planning on implementing graphical reporting. However, between-test heterogeneity was high and in many cases graphical elements may add little clinical utility, particularly if these merely reinforce information already contained in text based reports.

Background: Image bioinformatics infrastructure typically relies on a combination of server-side high-performance computing and client desktop applications tailored for graphic rendering. On the server side, matrix manipulation environments are often used as the back-end where deployment of specialized analytical workflows takes place. However, neither the server-side nor the client-side desktop solution, by themselves or combined, is conducive to the emergence of open, collaborative, computational ecosystems for image analysis that are both self-sustained and user driven. Materials and Methods: ImageJS was developed as a browser-based webApp, untethered from a server-side backend, by making use of recent advances in the modern web browser such as a very efficient compiler, high-end graphical rendering capabilities, and I/O tailored for code migration. Results : Multiple versioned code hosting services were used to develop distinct ImageJS modules to illustrate its amenability to collaborative deployment without compromise of reproducibility or provenance. The illustrative examples include modules for image segmentation, feature extraction, and filtering. The deployment of image analysis by code migration is in sharp contrast with the more conventional, heavier, and less safe reliance on data transfer. Accordingly, code and data are loaded into the browser by exactly the same script tag loading mechanism, which offers a number of interesting applications that would be hard to attain with more conventional platforms, such as NIH's popular ImageJ application. Conclusions : The modern web browser was found to be advantageous for image bioinformatics in both the research and clinical environments. This conclusion reflects advantages in deployment scalability and analysis reproducibility, as well as the critical ability to deliver advanced computational statistical procedures machines where access to sensitive data is controlled, that is, without local "download and installation."

Background: The use of adjuvant tamoxifen therapy in the treatment of estrogen receptor (ER) expressing breast carcinomas represents a major advance in personalized cancer treatment. Because there is no benefit (and indeed there is increased morbidity and mortality) associated with the use of tamoxifen therapy in ER-negative breast cancer, its use is restricted to women with ER expressing cancers. However, correctly classifying cancers as ER positive or negative has been challenging given the high reported false negative test rates for ER expression in surgical specimens. In this paper I model practice recommendations using published information from clinical trials to address the question of whether there is a false negative test rate above which it is more efficacious to forgo ER testing and instead treat all patients with tamoxifen regardless of ER test results. Methods: I used data from randomized clinical trials to model two different hypothetical treatment strategies: (1) the current strategy of treating only ER positive women with tamoxifen and (2) an alternative strategy where all women are treated with tamoxifen regardless of ER test results. The variables used in the model are literature-derived survival rates of the different combinations of ER positivity and treatment with tamoxifen, varying true ER positivity rates and varying false negative ER testing rates. The outcome variable was hypothetical 10-year survival. Results: The model predicted that there will be a range of true ER rates and false negative test rates above which it would be more efficacious to treat all women with breast cancer with tamoxifen and forgo ER testing. This situation occurred with high true positive ER rates and false negative ER test rates in the range of 20-30%. Conclusions: It is hoped that this model will provide an example of the potential importance of diagnostic error on clinical outcomes and furthermore will give an example of how the effect of that error could be modeled using real-world data from clinical trials.

Introduction: We aim to determine to what degree whole-slide images (WSI) can be compressed without impacting the ability of the pathologist to distinguish benign from malignant tissues. An underlying goal is to demonstrate the utility of a visual discrimination model (VDM) for predicting observer performance. Materials and Methods: A total of 100 regions of interest (ROIs) from a breast biopsy whole-slide images at five levels of JPEG 2000 compression (8:1, 16:1, 32:1, 64:1, and 128:1) plus the uncompressed version were shown to six pathologists to determine benign versus malignant status. Results: There was a significant decrease in performance as a function of compression ratio (F = 14.58, P < 0.0001). The visibility of compression artifacts in the test images was predicted using a VDM. Just-noticeable difference (JND) metrics were computed for each image, including the mean, median, ≥90th percentiles, and maximum values. For comparison, PSNR (peak signal-to-noise ratio) and Structural Similarity (SSIM) were also computed. Image distortion metrics were computed as a function of compression ratio and averaged across test images. All of the JND metrics were found to be highly correlated and differed primarily in magnitude. Both PSNR and SSIM decreased with bit rate, correctly reflecting a loss of image fidelity with increasing compression. Observer performance as measured by the Receiver Operating Characteristic area under the curve (ROC Az) was nearly constant up to a compression ratio of 32:1, then decreased significantly for 64:1 and 128:1 compression levels. The initial decline in Az occurred around a mean JND of 3, Minkowski JND of 4, and 99th percentile JND of 6.5. Conclusion: Whole-slide images may be compressible to relatively high levels before impacting WSI interpretation performance. The VDM metrics correlated well with artifact conspicuity and human performance.

Background: It is expected that health information technology (HIT) will deliver a safer, more efficient and effective health care system. The aim of this study was to undertake a qualitative and video-ethnographic examination of the impact of information technologies on work processes in the reception area of a Microbiology Department, to ascertain what changed, how it changed and the impact of the change. Materials and Methods: The setting for this study was the microbiology laboratory of a large tertiary hospital in Sydney. The study consisted of qualitative (interview and focus group) data and observation sessions for the period August 2005 to October 2006 along with video footage shot in three sessions covering the original system and the two stages of the Cerner implementation. Data analysis was assisted by NVivo software and process maps were produced from the video footage. Results: There were two laboratory information systems observed in the video footage with computerized provider order entry introduced four months later. Process maps highlighted the large number of pre data entry steps with the original system whilst the newer system incorporated many of these steps in to the data entry stage. However, any time saved with the new system was offset by the requirement to complete some data entry of patient information not previously required. Other changes noted included the change of responsibilities for the reception staff and the physical changes required to accommodate the increased activity around the data entry area. Conclusions: Implementing a new HIT is always an exciting time for any environment but ensuring that the implementation goes smoothly and with minimal trouble requires the administrator and their team to plan well in advance for staff training, physical layout and possible staff resource reallocation.

Introduction: An automated system for differential white blood cell (WBC) counting based on morphology can make manual differential leukocyte counts faster and less tedious for pathologists and laboratory professionals. We present an automated system for isolation and classification of WBCs in manually prepared, Wright stained, peripheral blood smears from whole slide images (WSI). Methods: A simple, classification scheme using color information and morphology is proposed. The performance of the algorithm was evaluated by comparing our proposed method with a hematopathologist's visual classification. The isolation algorithm was applied to 1938 subimages of WBCs, 1804 of them were accurately isolated. Then, as the first step of a two-step classification process, WBCs were broadly classified into cells with segmented nuclei and cells with nonsegmented nuclei. The nucleus shape is one of the key factors in deciding how to classify WBCs. Ambiguities associated with connected nuclear lobes are resolved by detecting maximum curvature points and partitioning them using geometric rules. The second step is to define a set of features using the information from the cytoplasm and nuclear regions to classify WBCs using linear discriminant analysis. This two-step classification approach stratifies normal WBC types accurately from a whole slide image. Results: System evaluation is performed using a 10-fold cross-validation technique. Confusion matrix of the classifier is presented to evaluate the accuracy for each type of WBC detection. Experiments show that the two-step classification implemented achieves a 93.9% overall accuracy in the five subtype classification. Conclusion: Our methodology achieves a semiautomated system for the detection and classification of normal WBCs from scanned WSI. Further studies will be focused on detecting and segmenting abnormal WBCs, comparison of 20× and 40× data, and expanding the applications for bone marrow aspirates.

Background: Immunohistochemistry (IHC) is an important tool to identify and quantify expression of certain proteins (antigens) to gain insights into the molecular processes in a diseased tissue. However, it is a challenge for pathologists to remember the discriminative characteristics of the growing number of such antigens across multiple diseases. The complexity of their expression patterns, fueled by continuous discoveries in molecular pathology, gives rise to a combinatorial explosion that places an unprecedented burden on a practicing pathologist and therefore increases cost and variability of IHC studies. Materials and Methods: To tackle these issues, we have developed antibody test optimized selection method, a novel informatics tool to help pathologists in improving the IHC antibody selection process. The method uses extensions of Shannon's information entropies and Bayesian probabilities to dynamically build an efficient diagnostic tree. Results: A comparative analysis of our method with the expert and World Health Organization classification guidelines showed that the proposed method brings threefold reduction in number of antibody tests required to reach a diagnostic conclusion. Conclusion: The developed method can significantly streamline the antibody test selection process, decrease associated costs and reduce inter- and intrapathologist variability in IHC decision-making.

Background: The Tissue Microarray Data Exchange Specification (TMA DES) is an XML specification for encoding TMA experiment data. While TMA DES data is encoded in XML, the files that describe its syntax, structure, and semantics are not. The DTD format is used to describe the syntax and structure of TMA DES, and the ISO 11179 format is used to define the semantics of TMA DES. However, XML Schema can be used in place of DTDs, and another XML encoded format, RDF, can be used in place of ISO 11179. Encoding all TMA DES data and metadata in XML would simplify the development and usage of programs which validate and parse TMA DES data. XML Schema has advantages over DTDs such as support for data types, and a more powerful means of specifying constraints on data values. An advantage of RDF encoded in XML over ISO 11179 is that XML defines rules for encoding data, whereas ISO 11179 does not. Materials and Methods: We created an XML Schema version of the TMA DES DTD. We wrote a program that converted ISO 11179 definitions to RDF encoded in XML, and used it to convert the TMA DES ISO 11179 definitions to RDF. Results: We validated a sample TMA DES XML file that was supplied with the publication that originally specified TMA DES using our XML Schema. We successfully validated the RDF produced by our ISO 11179 converter with the W3C RDF validation service. Conclusions: All TMA DES data could be encoded using XML, which simplifies its processing. XML Schema allows datatypes and valid value ranges to be specified for CDEs, which enables a wider range of error checking to be performed using XML Schemas than could be performed using DTDs.

Context: Whole slide imaging (WSI) for digital pathology involves the rapid automated acquisition of multiple high-power fields from a microscope slide containing a tissue specimen. Capturing each field in the correct focal plane is essential to create high-quality digital images. Others have described a novel focusing method which reduces the number of focal planes required to generate accurate focus. However, this method was not applied dynamically in an automated WSI system under continuous motion. Aims: This report measures the accuracy of this method when applied in a rapid continuous scan mode using a dual sensor WSI system with interleaved acquisition of images. Methods: We acquired over 400 tiles in a "stop and go" scan mode, surveying the entire z depth in each tile and used this as ground truth. We compared this ground truth focal height to the focal height determined using a rapid 3-point focus algorithm applied dynamically in a continuous scanning mode. Results: Our data showed the average focal height error of 0.30 (±0.27) μm compared to ground truth, which is well within the system's depth of field. On a tile by tile assessment, approximately 95% of the tiles were within the system's depth of field. Further, this method was six times faster than acquiring tiles compared to the same method in a non-continuous scan mode. Conclusions: The data indicates that the method employed can yield a significant improvement in scan speed while maintaining highly accurate autofocusing.

Background: Identification of individual prostatic glandular structures is an important prerequisite to quantitative histological analysis of prostate cancer with the aid of a computer. We have developed a computer method to segment individual glandular units and to extract quantitative image features, for computer identification of prostatic adenocarcinoma. Methods: Two sets of digital histology images were used: database I (n = 57) for developing and testing the computer technique, and database II (n = 116) for independent validation. The segmentation technique was based on a k-means clustering and a region-growing method. Computer segmentation results were evaluated subjectively and also compared quantitatively against manual gland outlines, using the Jaccard similarity measure. Quantitative features that were extracted from the computer segmentation results include average gland size, spatial gland density, and average gland circularity. Linear discriminant analysis (LDA) was used to combine quantitative image features. Classification performance was evaluated with receiver operating characteristic (ROC) analysis and the area under the ROC curve (AUC). Results: Jaccard similarity coefficients between computer segmentation and manual outlines of individual glands were between 0.63 and 0.72 for non-cancer and between 0.48 and 0.54 for malignant glands, respectively, similar to an interobserver agreement of 0.79 for non-cancer and 0.75 for malignant glands, respectively. The AUC value for the features of average gland size and gland density combined via LDA was 0.91 for database I and 0.96 for database II. Conclusions: Using a computer, we are able to delineate individual prostatic glands automatically and identify prostatic adenocarcinoma accurately, based on the quantitative image features extracted from computer-segmented glandular structures.

Background: The systematic analysis of imaged pathology specimens often results in a vast amount of morphological information at both the cellular and sub-cellular scales. While microscopy scanners and computerized analysis are capable of capturing and analyzing data rapidly, microscopy image data remain underutilized in research and clinical settings. One major obstacle which tends to reduce wider adoption of these new technologies throughout the clinical and scientific communities is the challenge of managing, querying, and integrating the vast amounts of data resulting from the analysis of large digital pathology datasets. This paper presents a data model, which addresses these challenges, and demonstrates its implementation in a relational database system. Context: This paper describes a data model, referred to as Pathology Analytic Imaging Standards (PAIS), and a database implementation, which are designed to support the data management and query requirements of detailed characterization of micro-anatomic morphology through many interrelated analysis pipelines on whole-slide images and tissue microarrays (TMAs). Aims: (1) Development of a data model capable of efficiently representing and storing virtual slide related image, annotation, markup, and feature information. (2) Development of a database, based on the data model, capable of supporting queries for data retrieval based on analysis and image metadata, queries for comparison of results from different analyses, and spatial queries on segmented regions, features, and classified objects. Settings and Design: The work described in this paper is motivated by the challenges associated with characterization of micro-scale features for comparative and correlative analyses involving whole-slides tissue images and TMAs. Technologies for digitizing tissues have advanced significantly in the past decade. Slide scanners are capable of producing high-magnification, high-resolution images from whole slides and TMAs within several minutes. Hence, it is becoming increasingly feasible for basic, clinical, and translational research studies to produce thousands of whole-slide images. Systematic analysis of these large datasets requires efficient data management support for representing and indexing results from hundreds of interrelated analyses generating very large volumes of quantifications such as shape and texture and of classifications of the quantified features. Materials and Methods: We have designed a data model and a database to address the data management requirements of detailed characterization of micro-anatomic morphology through many interrelated analysis pipelines. The data model represents virtual slide related image, annotation, markup and feature information. The database supports a wide range of metadata and spatial queries on images, annotations, markups, and features. Results: We currently have three databases running on a Dell PowerEdge T410 server with CentOS 5.5 Linux operating system. The database server is IBM DB2 Enterprise Edition 9.7.2. The set of databases consists of 1) a TMA database containing image analysis results from 4740 cases of breast cancer, with 641 MB storage size; 2) an algorithm validation database, which stores markups and annotations from two segmentation algorithms and two parameter sets on 18 selected slides, with 66 GB storage size; and 3) an in silico brain tumor study database comprising results from 307 TCGA slides, with 365 GB storage size. The latter two databases also contain human-generated annotations and markups for regions and nuclei. Conclusions: Modeling and managing pathology image analysis results in a database provide immediate benefits on the value and usability of data in a research study. The database provides powerful query capabilities, which are otherwise difficult or cumbersome to support by other approaches such as programming languages. Standardized, semantic annotated data representation and interfaces also make it possible to more efficiently share image data and analysis results.

Background: Here, we report the first use of a commercial prototype of full-field optical coherence tomography called Light-CT ^TM . Based on the principle of white light interferometry, Light-CT ^TM generates quick high-resolution three-dimensional tomographic images from unprocessed tissues. Its advantage over the current intra-surgical diagnostic standard, i.e. frozen section analysis, lies in the absence of freezing artifacts, which allows real-time diagnostic impressions, and/or for the tissues to be triaged for subsequent conventional histopathology. Materials and Methods: In this study, we recapitulate known normal histology in nine formalin fixed ex vivo rat organs (skin, heart, lung, liver, stomach, kidney, prostate, urinary bladder, and testis). Large surface and virtually sectioned stacks of images at varying depths were acquired by a pair of 10x/0.3 numerical aperture water immersion objectives, processed and visualized in real time. Results: Normal histology of the following organs was recapitulated by identifying various tissue microstructures. Skin: epidermis, dermal-epidermal junction and hair follicles with surrounding sebaceous glands in the dermis. Stomach: mucosa with surface pits, submucosa, muscularis propria and serosa. Liver: hepatocytes separated by sinusoidal spaces, central veins and portal triad. Kidney: convoluted tubules, medullary rays (straight tubules) and collecting ducts. Prostate: acini and fibro-muscular stroma. Lung: bronchi, bronchioles, alveolar ducts, alveoli and pleura. Urinary bladder: urothelium, lamina propria, muscularis propria, and serosa. Testis: seminiferous tubules with intra-tubular sperms. Conclusion: Light-CT ^TM is a powerful imaging tool to perform fast histology on fresh and fixed tissues, without introducing artifacts. Its compact size, ease of handling, fast image acquisition and safe incident light levels makes it well-suited for various intra-operative and intra-procedural triaging and decision making applications.

Background: Telemedicine has emerged as an efficient means of distributing professional medical expertise over a broad geographic area with few limitations to the various services that can be provided around the globe. Telepathology is particularly well suited to distributing subspecialty expertise in certain environments in an economical fashion, while preserving centers of excellence. Materials and Methods: After a decade of intrainstitutional teleneuropathology for intraoperative consultation, we expanded our practice to cross state lines and communicate between geographically and financially separate medical centers. Results: The result was an effective means of distributing neuropathological expertise while at the same time preserving a professional center of excellence. While technical and legal (i.e., physician licensing) barriers were surmounted, expected and unexpected issues related to communication required commitment on the part of multiple individuals with diverse expertise and responsibilities. Conclusion: Lessons learned from this successful venture can be used to facilitate future efforts in this ever-growing practical vehicle for distributing pathology subspecialty expertise.

Background: The Tissue Microarray Data Exchange Specification (TMA DES) is an eXtensible Markup Language (XML) specification for encoding TMA experiment data in a machine-readable format that is also human readable. TMA DES defines Common Data Elements (CDEs) that form a basic vocabulary for describing TMA data. TMA data are routinely subjected to univariate and multivariate statistical analysis to determine differences or similarities between pathologically distinct groups of tumors for one or more markers or between markers for different groups. Such statistical analysis tests include the t-test, ANOVA, Chi-square, Mann-Whitney U, and Kruskal-Wallis tests. All these generate output that needs to be recorded and stored with TMA data. Materials and Methods: We propose extending the TMA DES to include syntactic and semantic definitions of CDEs for describing the results of statistical analyses performed upon TMA DES data. These CDEs are described in this paper and it is illustrated how they can be added to the TMA DES. We created a Document Type Definition (DTD) file defining the syntax for these CDEs, and a set of ISO 11179 entries providing semantic definitions for them. We describe how we wrote a program in R that read TMA DES data from an XML file, performed statistical analyses on that data, and created a new XML file containing both the original XML data and CDEs representing the results of our analyses. This XML file was submitted to XML parsers in order to confirm that they conformed to the syntax defined in our extended DTD file. TMA DES XML files with deliberately introduced errors were also parsed in order to verify that our new DTD file could perform error checking. Finally, we also validated an existing TMA DES XML file against our DTD file in order to demonstrate the backward compatibility of our DTD. Results: Our experiments demonstrated the encoding of analysis results using our proposed CDEs. We used XML parsers to confirm that these XML data were syntactically correct and conformed to the rules specified in our extended TMA DES DTD. We also demonstrated that this extended DTD was capable of being used to successfully perform error checking, and was backward compatible with pre-existing TMA DES data which did not use our new CDEs. Conclusions: The TMA DES allows Tissue Microarray data to be shared. A variety of statistical tests are used to analyze such data. We have proposed a set of CDEs as an extension to the TMA DES which can be used to annotate TMA DES data with the results of statistical analyses performed on that data. We performed experiments which demonstrated the usage of TMA DES data containing our proposed CDEs.

Background: Tissue MicroArrays (TMAs) are a high throughput technology for rapid analysis of protein expression across hundreds of patient samples. Often, data relating to TMAs is specific to the clinical trial or experiment it is being used for, and not interoperable. The Tissue Microarray Data Exchange Specification (TMA DES) is a set of eXtensible Markup Language (XML)-based protocols for storing and sharing digitized Tissue Microarray data. XML data are enclosed by named tags which serve as identifiers. These tag names can be Common Data Elements (CDEs), which have a predefined meaning or semantics. By using this specification in a laboratory setting with increasing demands for digital pathology integration, we found that the data structure lacked the ability to cope with digital slide imaging in respect to web-enabled digital pathology systems and advanced scoring techniques. Materials and Methods: By employing user centric design, and observing behavior in relation to TMA scoring and associated data, the TMA DES format was extended to accommodate the current limitations. This was done with specific focus on developing a generic tool for handling any given scoring system, and utilizing data for multiple observations and observers. Results: DTDs were created to validate the extensions of the TMA DES protocol, and a test set of data containing scores for 6,708 TMA core images was generated. The XML was then read into an image processing algorithm to utilize the digital pathology data extensions, and scoring results were easily stored alongside the existing multiple pathologist scores. Conclusions: By extending the TMA DES format to include digital pathology data and customizable scoring systems for TMAs, the new system facilitates the collaboration between pathologists and organizations, and can be used in automatic or manual data analysis. This allows complying systems to effectively communicate complex and varied scoring data.

Background: Adoption of digital images for pathological specimens has been slower than adoption of digital images in radiology, despite a number of anticipated advantages for digital images in pathology. In this paper, we explore the factors that might explain this slower rate of adoption. Materials and Method: Semi-structured interviews on barriers and facilitators to the adoption of digital images were conducted with two radiologists, three pathologists, and one pathologist's assistant. Results: Barriers and facilitators to adoption of digital images were reported in the areas of performance, workflow-efficiency, infrastructure, integration with other software, and exposure to digital images. The primary difference between the settings was that performance with the use of digital images as compared to the traditional method was perceived to be higher in radiology and lower in pathology. Additionally, exposure to digital images was higher in radiology than pathology, with some radiologists exclusively having been trained and/or practicing with digital images. The integration of digital images both improved and reduced efficiency in routine and non-routine workflow patterns in both settings, and was variable across the different organizations. A comparison of these findings with prior research on adoption of other health information technologies suggests that the barriers to adoption of digital images in pathology are relatively tractable. Conclusions: Improving performance using digital images in pathology would likely accelerate adoption of innovative technologies that are facilitated by the use of digital images, such as electronic imaging databases, electronic health records, double reading for challenging cases, and computer-aided diagnostic systems.

Background: Clinical records are often unstructured, free-text documents that create information extraction challenges and costs. Healthcare delivery and research organizations, such as the National Mesothelioma Virtual Bank, require the aggregation of both structured and unstructured data types. Natural language processing offers techniques for automatically extracting information from unstructured, free-text documents. Methods: Five hundred and eight history and physical reports from mesothelioma patients were split into development (208) and test sets (300). A reference standard was developed and each report was annotated by experts with regard to the patient's personal history of ancillary cancer and family history of any cancer. The Hx application was developed to process reports, extract relevant features, perform reference resolution and classify them with regard to cancer history. Two methods, Dynamic-Window and ConText, for extracting information were evaluated. Hx's classification responses using each of the two methods were measured against the reference standard. The average Cohen's weighted kappa served as the human benchmark in evaluating the system. Results: Hx had a high overall accuracy, with each method, scoring 96.2%. F-measures using the Dynamic-Window and ConText methods were 91.8% and 91.6%, which were comparable to the human benchmark of 92.8%. For the personal history classification, Dynamic-Window scored highest with 89.2% and for the family history classification, ConText scored highest with 97.6%, in which both methods were comparable to the human benchmark of 88.3% and 97.2%, respectively. Conclusion: We evaluated an automated application's performance in classifying a mesothelioma patient's personal and family history of cancer from clinical reports. To do so, the Hx application must process reports, identify cancer concepts, distinguish the known mesothelioma from ancillary cancers, recognize negation, perform reference resolution and determine the experiencer. Results indicated that both information extraction methods tested were dependant on the domain-specific lexicon and negation extraction. We showed that the more general method, ConText, performed as well as our task-specific method. Although Dynamic-Window could be modified to retrieve other concepts, ConText is more robust and performs better on inconclusive concepts. Hx could greatly improve and expedite the process of extracting data from free-text, clinical records for a variety of research or healthcare delivery organizations.

Background: The Early Detection Research Network (EDRN) colorectal and pancreatic neoplasm virtual biorepository is a bioinformatics-driven system that provides high-quality clinicopathology-rich information for clinical biospecimens. This NCI-sponsored EDRN resource supports translational cancer research. The information model of this biorepository is based on three components: (a) development of common data elements (CDE), (b) a robust data entry tool and (c) comprehensive data query tools. Methods: The aim of the EDRN initiative is to develop and sustain a virtual biorepository for support of translational research. High-quality biospecimens were accrued and annotated with pertinent clinical, epidemiologic, molecular and genomic information. A user-friendly annotation tool and query tool was developed for this purpose. The various components of this annotation tool include: CDEs are developed from the College of American Pathologists (CAP) Cancer Checklists and North American Association of Central Cancer Registries (NAACR) standards. The CDEs provides semantic and syntactic interoperability of the data sets by describing them in the form of metadata or data descriptor. The data entry tool is a portable and flexible Oracle-based data entry application, which is an easily mastered, web-based tool. The data query tool facilitates investigators to search deidentified information within the warehouse through a "point and click" interface thus enabling only the selected data elements to be essentially copied into a data mart using a dimensional-modeled structure from the warehouse's relational structure. Results: The EDRN Colorectal and Pancreatic Neoplasm Virtual Biorepository database contains multimodal datasets that are available to investigators via a web-based query tool. At present, the database holds 2,405 cases and 2,068 tumor accessions. The data disclosure is strictly regulated by user's authorization. The high-quality and well-characterized biospecimens have been used in different translational science research projects as well as to further various epidemiologic and genomics studies. Conclusions: The EDRN Colorectal and Pancreatic Neoplasm Virtual Biorepository with a tangible translational biomedical informatics infrastructure facilitates translational research. The data query tool acts as a central source and provides a mechanism for researchers to efficiently query clinically annotated datasets and biospecimens that are pertinent to their research areas. The tool ensures patient health information protection by disclosing only deidentified data with Institutional Review Board and Health Insurance Portability and Accountability Act protocols.

Background: Radio frequency identification (RFID) tags have potential for use in identifying and tracking biospecimens in anatomic pathology and biorepository laboratories. However, there is little to no data on the tolerance of tags to solutions, solvents, temperatures, and pressures likely to be encountered in the laboratory. The functioning of the Hitachi Mu-chip RFID tag, a candidate for pathology use, was evaluated under such conditions. Methods: The RFID tags were affixed to cryovials containing tissue or media, glass slides, and tissue cassettes. The tags were interrogated for readability before and after each testing condition or cycle. Individual tags were subjected to only one testing condition but for multiple cycles. Testing conditions were: 1) Ten wet autoclave cycles (121˚C, 15 psi); 2) Ten dry autoclave cycles (121˚C, 26 psi); 3) Ten tissue processor cycles; 4) Ten hematoxylin and eosin (H&E) staining cycles; 5) Ten antigen retrieval pressure cooker cycles (125˚C, 15 psi); 6) 75 ^o C for seven days; 7) 75-59 ^o C day/night cycles for 7 days; 8) -80 ^o C, -150 ^o C, or -196 ^o C for 12 months; 9) Fifty freeze-thaw cycles (-196 ^o C to 22 ^o C). Results: One hundred percent of tags exposed to cold temperatures from -80 to -196 ^o C (80 tags, 1120 successful reads), high temperatures from 52 to 75 ^o C (40 tags, 420 reads), H & E staining (20 tags, 200 reads), pressure cooker antigen retrieval (20 tags, 200 reads), and wet autoclaving (20 tags, 200 reads) functioned well throughout and after testing. Of note, all 20 tested tags tolerated 50 freeze-thaw cycles and all 60 tags subjected to sustained freezing temperatures were readable after 1 year. One dry autoclaved tag survived nine cycles but failed after the tenth. The remaining 19 tags were readable after all 10 dry autoclave cycles. One tag failed after the first tissue processing cycle while the remaining 19 tags survived all 10 tissue processing cycles. Conclusions: In this preliminary study, these RFID tags show a high-degree of tolerance to tested solutions, solvents, temperature, and pressure conditions. However, a measurable failure rate is detectable under some circumstances and redundant identification systems such as barcodes may be required with the deployment of RFID systems. We have delineated testing protocols that may be used as a framework for preliminary assessments of candidate RFID tag tolerance to laboratory conditions.