Introduction: The White Blood Cell (WBC) differential count yields clinically relevant information about health and disease. Currently, pathologists manually annotate the WBCs, which is time consuming and susceptible to error, due to the tedious nature of the process. This study aims at automation of the Differential Blood Count (DBC) process, so as to increase productivity and eliminate human errors. Materials and Methods: The proposed system takes the peripheral Leishman blood stain images as the input and generates a count for each of the WBC subtypes. The digitized microscopic images are stain normalized for the segmentation, to be consistent over a diverse set of slide images. Active contours are employed for robust segmentation of the WBC nucleus and cytoplasm. The seed points are generated by processing the images in Hue-Saturation-Value (HSV) color space. An efficient method for computing a new feature, 'number of lobes,' for discrimination of WBC subtypes, is introduced in this article. This method is based on the concept of minimization of the compactness of each lobe. The Naive Bayes classifier, with Laplacian correction, provides a fast, efficient, and robust solution to multiclass categorization problems. This classifier is characterized by incremental learning and can also be embedded within the database systems. Results: An overall accuracy of 92.45% and 92.72% over the training and testing sets has been obtained, respectively. Conclusion: Thus, incremental learning is inducted into the Naive Bayes Classifier, to facilitate fast, robust, and efficient classification, which is evident from the high sensitivity achieved for all the subtypes of WBCs.

Background: The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples. Materials and Methods: The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue. Results: We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert. Conclusions: Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many applications, ranging from antibody quality control to tumor grading.

Background: Tissue microarrays (TMAs) are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC) scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localization of regions of invasive and in-situ carcinoma followed by ordinal IHC scoring of nuclei in these regions is proposed. The localization stage classifies locations on a grid as tumor or non-tumor based on local image features. These classifications are then refined using an auto-context algorithm called spin-context. Spin-context uses a series of classifiers to integrate image feature information with spatial context information in the form of estimated class probabilities. This is achieved in a rotationally-invariant manner. The second stage estimates ordinal IHC scores in terms of the strength of staining and the proportion of nuclei stained. These estimates take the form of posterior probabilities, enabling images with uncertain scores to be referred for pathologist review. Results: The method was validated against manual pathologist scoring on two nuclear markers, progesterone receptor (PR) and estrogen receptor (ER). Errors for PR data were consistently lower than those achieved with ER data. Scoring was in terms of estimated proportion of cells that were positively stained (scored on an ordinal scale of 0-6) and perceived strength of staining (scored on an ordinal scale of 0-3). Average absolute differences between predicted scores and pathologist-assigned scores were 0.74 for proportion of cells and 0.35 for strength of staining (PR). Conclusions: The use of context information via spin-context improved the precision and recall of tumor localization. The combination of the spin-context localization method with the automated scoring method resulted in reduced IHC scoring errors.

Context: According to Nottingham grading system, mitosis count in breast cancer histopathology is one of three components required for cancer grading and prognosis. Manual counting of mitosis is tedious and subject to considerable inter- and intra-reader variations. Aims: The aim is to investigate the various texture features and Hierarchical Model and X (HMAX) biologically inspired approach for mitosis detection using machine-learning techniques. Materials and Methods: We propose an approach that assists pathologists in automated mitosis detection and counting. The proposed method, which is based on the most favorable texture features combination, examines the separability between different channels of color space. Blue-ratio channel provides more discriminative information for mitosis detection in histopathological images. Co-occurrence features, run-length features, and Scale-invariant feature transform (SIFT) features were extracted and used in the classification of mitosis. Finally, a classification is performed to put the candidate patch either in the mitosis class or in the non-mitosis class. Three different classifiers have been evaluated: Decision tree, linear kernel Support Vector Machine (SVM), and non-linear kernel SVM. We also evaluate the performance of the proposed framework using the modified biologically inspired model of HMAX and compare the results with other feature extraction methods such as dense SIFT. Results: The proposed method has been tested on Mitosis detection in breast cancer histological images (MITOS) dataset provided for an International Conference on Pattern Recognition (ICPR) 2012 contest. The proposed framework achieved 76% recall, 75% precision and 76% F-measure. Conclusions: Different frameworks for classification have been evaluated for mitosis detection. In future work, instead of regions, we intend to compute features on the results of mitosis contour segmentation and use them to improve detection and classification rate.

Aims: A methodology for quantitative comparison of histological stains based on their classification and clustering performance, which may facilitate the choice of histological stains for automatic pattern and image analysis. Background: Machine learning and image analysis are becoming increasingly important in pathology applications for automatic analysis of histological tissue samples. Pathologists rely on multiple, contrasting stains to analyze tissue samples, but histological stains are developed for visual analysis and are not always ideal for automatic analysis. Materials and Methods: Thirteen different histological stains were used to stain adjacent prostate tissue sections from radical prostatectomies. We evaluate the stains for both supervised and unsupervised classification of stain/tissue combinations. For supervised classification we measure the error rate of nonlinear support vector machines, and for unsupervised classification we use the Rand index and the F-measure to assess the clustering results of a Gaussian mixture model based on expectation-maximization. Finally, we investigate class separability measures based on scatter criteria. Results: A methodology for quantitative evaluation of histological stains in terms of their classification and clustering efficacy that aims at improving segmentation and color decomposition. We demonstrate that for a specific tissue type, certain stains perform consistently better than others according to objective error criteria. Conclusions: The choice of histological stain for automatic analysis must be based on its classification and clustering performance, which are indicators of the performance of automatic segmentation of tissue into morphological components, which in turn may be the basis for diagnosis.

Introduction: The registration of histological whole slide images is an important prerequisite for modern histological image analysis. A partial reconstruction of the original volume allows e.g. colocalization analysis of tissue parameters or high-detail reconstructions of anatomical structures in 3D. Methods: In this paper, we present an automatic staining-invariant registration method, and as part of that, introduce a novel vessel-based rigid registration algorithm using a custom similarity measure. The method is based on an iterative best-fit matching of prominent vessel structures. Results: We evaluated our method on a sophisticated synthetic dataset as well as on real histological whole slide images. Based on labeled vessel structures we compared the relative differences for corresponding structures. The average positional error was close to 0, the median for the size change factor was 1, and the median overlap was 0.77. Conclusion: The results show that our approach is very robust and creates high quality reconstructions. The key element for the resulting quality is our novel rigid registration algorithm.

Context: Mosaics of Whole Slides (WS) are a valuable resource for pathologists to have the whole sample available at high resolution. The WS mosaic provides pathologists with an overview of the whole sample at a glance, helping them to make a reliable diagnosis. Despite recent solutions exist for creating WS mosaics based, for instance, on automated microscopes with motorized stages or WS scanner, most of the histopathology analysis are still performed in laboratories endowed with standard manual stage microscopes. Nowadays, there are lots of dedicated devices and hardware to achieve WS automatically and in batch, but only few of them are conceived to work tightly connected with a microscope and none of them is capable of working in real-time with common light microscopes. However, there is a need of having low-cost yet effective mosaicing applications even in small laboratories to improve routine histopathological analyses or to perform remote diagnoses. Aims: The purpose of this work is to study and develop a real-time mosaicing algorithm working even using non-automated microscopes, to enable pathologists to achieve WS while moving the holder manually, without exploiting any dedicated device. This choice enables pathologists to build WS in real-time, while browsing the sample as they are accustomed to, helping them to identify, locate, and digitally annotate lesions fast. Materials and Methods: Our method exploits fast feature tracker and frame to frame registration that we implemented on common graphics processing unit cards. The system work with common light microscopes endowed with a digital camera and connected to a commodity personal computer. Result and Conclusion: The system has been tested on several histological samples to test the effectiveness of the algorithm to work with mosaicing having different appearances as far as brightness, contrast, texture, and detail levels are concerned, attaining sub-pixel registration accuracy at real-time interactive rates.

Introduction: The notion of local scale was introduced to characterize varying levels of image detail so that localized image processing tasks could be performed while simultaneously yielding a globally optimal result. In this paper, we have presented the methodological framework for a novel locally adaptive scale definition, morphologic scale (MS), which is different from extant local scale definitions in that it attempts to characterize local heterogeneity as opposed to local homogeneity. Methods: At every point of interest, the MS is determined as a series of radial paths extending outward in the direction of least resistance, navigating around obstructions. Each pixel can then be directly compared to other points of interest via a rotationally invariant quantitative feature descriptor, determined by the application of Fourier descriptors to the collection of these paths. Results: Our goal is to distinguish tumor and stromal tissue classes in the context of four different digitized pathology datasets: prostate tissue microarrays (TMAs) stained with hematoxylin and eosin (HE) (44 images) and TMAs stained with only hematoxylin (H) (44 images), slide mounts of ovarian H (60 images), and HE breast cancer (51 images) histology images. Classification performance over 50 cross-validation runs using a Bayesian classifier produced mean areas under the curve of 0.88 ± 0.01 (prostate HE), 0.87 ± 0.02 (prostate H), 0.88 ± 0.01 (ovarian H), and 0.80 ± 0.01 (breast HE). Conclusion: For each dataset listed in [Table 3], we randomly selected 100 points per image, and using the procedure described in Experiment 1, we attempted to separate them as belonging to stroma or epithelium.

Context: Three dimensional (3D) tissue reconstructions from the histology images with different stains allows the spatial alignment of structural and functional elements highlighted by different stains for quantitative study of many physiological and pathological phenomena. This has significant potential to improve the understanding of the growth patterns and the spatial arrangement of diseased cells, and enhance the study of biomechanical behavior of the tissue structures towards better treatments (e.g. tissue-engineering applications). Methods: This paper evaluates three strategies for 3D reconstruction from sets of two dimensional (2D) histological sections with different stains, by combining methods of 2D multi-stain registration and 3D volumetric reconstruction from same stain sections. Setting and Design: The different strategies have been evaluated on two liver specimens (80 sections in total) stained with Hematoxylin and Eosin (H and E), Sirius Red, and Cytokeratin (CK) 7. Results and Conclusion: A strategy of using multi-stain registration to align images of a second stain to a volume reconstructed by same-stain registration results in the lowest overall error, although an interlaced image registration approach may be more robust to poor section quality.

Background: As a critical technique in a digital pathology laboratory, automatic nuclear detection has been investigated for more than one decade. Conventional methods work on the raw images directly whose color/intensity homogeneity within tissue/cell areas are undermined due to artefacts such as uneven staining, making the subsequent binarization process prone to error. This paper concerns detecting cell nuclei automatically from digital pathology images by enhancing the color homogeneity as a pre-processing step. Methods: Unlike previous watershed based algorithms relying on post-processing of the watershed, we present a new method that incorporates the staining information of pathological slides in the analysis. This pre-processing step strengthens the color homogeneity within the nuclear areas as well as the background areas, while keeping the nuclear edges sharp. Proof of convergence for the proposed algorithm is also provided. After pre-processing, Otsu's threshold is applied to binarize the image, which is further segmented via watershed. To keep a proper compromise between removing overlapping and avoiding over-segmentation, a naive Bayes classifier is designed to refine the splits suggested by the watershed segmentation. Results: The method is validated with 10 sets of 1000 × 1000 pathology images of lymphoma from one digital slide. The mean precision and recall rates are 87% and 91%, corresponding to a mean F-score equal to 89%. Standard deviations for these performance indicators are 5.1%, 1.6% and 3.2% respectively. Conclusion: The precision/recall performance obtained indicates that the proposed method outperforms several other alternatives. In particular, for nuclear detection, stain guided mean-shift (SGMS) is more effective than the direct application of mean-shift in pre-processing. Our experiments also show that pre-processing the digital pathology images with SGMS gives better results than conventional watershed algorithms. Nevertheless, as only one type of tissue is tested in this paper, a further study is planned to enhance the robustness of the algorithm so that other types of tissues/stains can also be processed reliably.

Introduction: Research and diagnosis in medicine and biology often require the assessment of a large amount of microscopy image data. Although on the one hand, digital pathology and new bioimaging technologies find their way into clinical practice and pharmaceutical research, some general methodological issues in automated image analysis are still open. Methods: In this study, we address the problem of fitting the parameters in a microscopy image segmentation pipeline. We propose to fit the parameters of the pipeline's modules with optimization algorithms, such as, genetic algorithms or coordinate descents, and show how visual exploration of the parameter space can help to identify sub-optimal parameter settings that need to be avoided. Results: This is of significant help in the design of our automatic parameter fitting framework, which enables us to tune the pipeline for large sets of micrographs. Conclusion: The underlying parameter spaces pose a challenge for manual as well as automated parameter optimization, as the parameter spaces can show several local performance maxima. Hence, optimization strategies that are not able to jump out of local performance maxima, like the hill climbing algorithm, often result in a local maximum.

Background: Multispectral microscopy and multiple staining can be used to identify cells with distinct immunohistochemical (IHC) characteristics. We present here a method called hypothesized interaction distribution (HID) analysis for characterizing the statistical distribution of pair-wise spatial relationships between cells with particular IHC characteristics and apply it to clinical data. Materials and Methods: We retrospectively analyzed data from a study of 26 follicular lymphoma patients in which sections were stained for CD20 and YY1. HID analysis, using leave-one-out validation, was used to assign patients to one of two groups. We tested the null hypothesis of no difference in Kaplan-Meier survival curves between the groups. Results: Shannon entropy of HIDs assigned patients to groups that had significantly different survival curves (median survival was 7.70 versus 110 months, P = 0.00750). Hypothesized interactions between pairs of cells positive for both CD20 and YY1 were associated with poor survival. Conclusions: HID analysis provides quantitative inferences about possible interactions between spatially proximal cells with particular IHC characteristics. In follicular lymphoma, HID analysis was able to distinguish between patients with poor versus good survival, and it may have diagnostic and prognostic utility in this and other diseases.

Background: Histology sections provide accurate information on atherosclerotic plaque composition, and are used in various applications. To our knowledge, no automated systems for plaque component segmentation in histology sections currently exist. Materials and Methods: We perform pixel-wise classification of fibrous, lipid, and necrotic tissue in Elastica Von Gieson-stained histology sections, using features based on color channel intensity and local image texture and structure. We compare an approach where we train on independent data to an approach where we train on one or two sections per specimen in order to segment the remaining sections. We evaluate the results on segmentation accuracy in histology, and we use the obtained histology segmentations to train plaque component classification methods in ex vivo Magnetic resonance imaging (MRI) and in vivo MRI and computed tomography (CT). Results: In leave-one-specimen-out experiments on 176 histology slices of 13 plaques, a pixel-wise accuracy of 75.7 ± 6.8% was obtained. This increased to 77.6 ± 6.5% when two manually annotated slices of the specimen to be segmented were used for training. Rank correlations of relative component volumes with manually annotated volumes were high in this situation (P = 0.82-0.98). Using the obtained histology segmentations to train plaque component classification methods in ex vivo MRI and in vivo MRI and CT resulted in similar image segmentations for training on the automated histology segmentations as for training on a fully manual ground truth. The size of the lipid-rich necrotic core was significantly smaller when training on fully automated histology segmentations than when manually annotated histology sections were used. This difference was reduced and not statistically significant when one or two slices per section were manually annotated for histology segmentation. Conclusions: Good histology segmentations can be obtained by automated segmentation, which show good correlations with ground truth volumes. In addition, these can be used to develop segmentation methods in other imaging modalities. Accuracy increases when one or two sections of the same specimen are used for training, which requires a limited amount of user interaction in practice.

Background: Histological tissue analysis often involves manual cell counting and staining estimation of cancerous cells. These assessments are extremely time consuming, highly subjective and prone to error, since immunohistochemically stained cancer tissues usually show high variability in cell sizes, morphological structures and staining quality. To facilitate reproducible analysis in clinical practice as well as for cancer research, objective computer assisted staining estimation is highly desirable. Methods: We employ machine learning algorithms as randomized decision trees and support vector machines for nucleus detection and classification. Superpixels as segmentation over the tissue image are classified into foreground and background and thereafter into malignant and benign, learning from the user's feedback. As a fast alternative without nucleus classification, the existing color deconvolution method is incorporated. Results: Our program TMARKER connects already available workflows for computational pathology and immunohistochemical tissue rating with modern active learning algorithms from machine learning and computer vision. On a test dataset of human renal clear cell carcinoma and prostate carcinoma, the performance of the used algorithms is equivalent to two independent pathologists for nucleus detection and classification. Conclusion: We present a novel, free and operating system independent software package for computational cell counting and staining estimation, supporting IHC stained tissue analysis in clinic and for research. Proprietary toolboxes for similar tasks are expensive, bound to specific commercial hardware (e.g. a microscope) and mostly not quantitatively validated in terms of performance and reproducibility. We are confident that the presented software package will proof valuable for the scientific community and we anticipate a broader application domain due to the possibility to interactively learn models for new image types.

Background: Segmentation of areas containing tumor cells in standard H&E histopathology images of breast (and several other tissues) is a key task for computer-assisted assessment and grading of histopathology slides. Good segmentation of tumor regions is also vital for automated scoring of immunohistochemical stained slides to restrict the scoring or analysis to areas containing tumor cells only and avoid potentially misleading results from analysis of stromal regions. Furthermore, detection of mitotic cells is critical for calculating key measures such as mitotic index; a key criteria for grading several types of cancers including breast cancer. We show that tumor segmentation can allow detection and quantification of mitotic cells from the standard H&E slides with a high degree of accuracy without need for special stains, in turn making the whole process more cost-effective. Method: Based on the tissue morphology, breast histology image contents can be divided into four regions: Tumor, Hypocellular Stroma (HypoCS), Hypercellular Stroma (HyperCS), and tissue fat (Background). Background is removed during the preprocessing stage on the basis of color thresholding, while HypoCS and HyperCS regions are segmented by calculating features using magnitude and phase spectra in the frequency domain, respectively, and performing unsupervised segmentation on these features. Results: All images in the database were hand segmented by two expert pathologists. The algorithms considered here are evaluated on three pixel-wise accuracy measures: precision, recall, and F1-Score. The segmentation results obtained by combining HypoCS and HyperCS yield high F1-Score of 0.86 and 0.89 with re­spect to the ground truth. Conclusions: In this paper, we show that segmentation of breast histopathology image into hypocellular stroma and hypercellular stroma can be achieved using magnitude and phase spectra in the frequency domain. The segmentation leads to demarcation of tumor margins leading to improved accuracy of mitotic cell detection.

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.

Data protection and security are critical components of routine pathology practice because laboratories are legally required to securely store and transmit electronic patient data. With increasing connectivity of information systems, laboratory work-stations, and instruments themselves to the Internet, the demand to continuously protect and secure laboratory information can become a daunting task. This review addresses informatics security issues in the pathology laboratory related to passwords, biometric devices, data encryption, internet security, virtual private networks, firewalls, anti-viral software, and emergency security situations, as well as the potential impact that newer technologies such as mobile devices have on the privacy and security of electronic protected health information (ePHI). In the United States, the Health Insurance Portability and Accountability Act (HIPAA) govern the privacy and protection of medical information and health records. The HIPAA security standards final rule mandate administrative, physical, and technical safeguards to ensure the confidentiality, integrity, and security of ePHI. Importantly, security failures often lead to privacy breaches, invoking the HIPAA privacy rule as well. Therefore, this review also highlights key aspects of HIPAA and its impact on the pathology laboratory in the United States.

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.

Objective: The ability to transfer image markup and annotation data from one scanned image of a slide to a newly acquired image of the same slide within a single vendor platform was investigated. The goal was to study the ability to use image markup and annotation data files as a mechanism to capture and retain pathologist knowledge without retaining the entire whole slide image (WSI) file. Methods: Accepted mathematical principles were investigated as a method to overcome variations in scans of the same glass slide and to accurately associate image markup and annotation data across different WSI of the same glass slide. Trilateration was used to link fixed points within the image and slide to the placement of markups and annotations of the image in a metadata file. Results: Variation in markup and annotation placement between WSI of the same glass slide was reduced from over 80 μ to less than 4 μ in the x-axis and from 17 μ to 6 μ in the y-axis ( P < 0.025). Conclusion: This methodology allows for the creation of a highly reproducible image library of histopathology images and interpretations for educational and research use.

Background: Interfacing complex laboratory equipment to laboratory information systems (LIS) has become a more commonly encountered problem in clinical laboratories, especially for instruments that do not have an interface provided by the vendor. Liquid chromatography-tandem mass spectrometry is a great example of such complex equipment, and has become a frequent addition to clinical laboratories. As the testing volume on such instruments can be significant, manual data entry will also be considerable and the potential for concomitant transcription errors arises. Due to this potential issue, our aim was to interface an AB SCIEX ^TM mass spectrometer to our Sunquest^® LIS. Materials and Methods: We licensed software for the data management interface from the University of Pittsburgh, but extended this work as follows: The interface was designed so that it would accept a text file exported from the AB SCIEX ^TM × 5500 QTrap^® mass spectrometer, pre-process the file (using newly written code) into the correct format and upload it into Sunquest^® via file transfer protocol. Results: The licensed software handled the majority of the interface tasks with the exception of converting the output from the Analyst^® software to the required Sunquest^® import format. This required writing of a "pre-processor" by one of the authors which was easily integrated with the supplied software. Conclusions: We successfully implemented the data management interface licensed from the University of Pittsburgh. Given the coding that was required to write the pre-processor, and alterations to the source code that were performed when debugging the software, we would suggest that before a laboratory decides to implement such an interface, it would be necessary to have a competent computer programmer available.

Digitized slides produced by whole slide image scanners can be easily shared over a network or by transferring image files to optical or other data storage devices. Navigation of digitized slides is interactive and intended to simulate viewing glass slides with a microscope (virtual microscopy). Image viewing software permits users to edit, annotate, analyze, and easily share whole slide images (WSI). As a result, WSI have begun to replace the traditional light microscope, offering a myriad of opportunities for education. This article focuses on current applications of WSI in education and proficiency testing. WSI has been successfully explored for graduate education (medical, dental, and veterinary schools), training of pathology residents, as an educational tool in allied pathology schools (e.g., cytotechnology), for virtual tracking and tutoring, tele-education (tele-conferencing), e-learning, virtual workshops, at tumor boards, with interactive publications, and on examinations. WSI supports flexible and cost-effective distant learning and augments problem-oriented teaching, competency evaluation, and proficiency testing. WSI viewed on touchscreen displays and with tablet technology are especially beneficial for education. Further investigation is necessary to develop superior WSI applications that better support education and to design viewing stations with ergonomic tools that improve the WSI-human interface and navigation of virtual slides. Studies to determine the impact of training pathologists without exposure to actual glass slides are also needed.

Several modes of telepathology exist including static (store-and-forward), dynamic (live video streaming or robotic microscopy), and hybrid technology involving whole slide imaging (WSI). Telepathology has been employed at the University of Pittsburgh Medical Center (UPMC) for over a decade at local, national, and international sites. All modes of telepathology have been successfully utilized to exploit our institutions subspecialty expertise and to compete for pathology services. This article discusses the experience garnered at UPMC with each of these teleconsultation methods. Static and WSI telepathology systems have been utilized for many years in transplant pathology using a private network and client-server architecture. Only minor clinically significant differences of opinion were documented. In hematopathology, the CellaVision^® system is used to transmit, via email, static images of blood cells in peripheral blood smears for remote interpretation. While live video streaming has remained the mode of choice for providing immediate adequacy assessment of cytology specimens by telecytology, other methods such as robotic microscopy have been validated and shown to be effective. Robotic telepathology has been extensively used to remotely interpret intra-operative neuropathology consultations (frozen sections). Adoption of newer technology and increased pathologist experience has improved accuracy and deferral rates in teleneuropathology. A digital pathology consultation portal (https://pathconsult.upmc.com/) was recently created at our institution to facilitate digital pathology second opinion consults, especially for WSI. The success of this web-based tool is the ability to handle vendor agnostic, large image files of digitized slides, and ongoing user-friendly customization for clients and teleconsultants. It is evident that the practice of telepathology at our institution has evolved in concert with advances in technology and user experience. Early and continued adoption of telepathology has promoted additional digital pathology resources that are now being leveraged for other clinical, educational, and research purposes.

In-house software development for use in a clinical laboratory is a controversial issue. Many of the objections raised are based on outdated software development practices, an exaggeration of the risks involved, and an underestimation of the benefits that can be realized. Buy versus build analyses typically do not consider total costs of ownership, and unfortunately decisions are often made by people who are not directly affected by the workflow obstacles or benefits that result from those decisions. We have been developing custom software for clinical use for over a decade, and this article presents our perspective on this practice. A complete analysis of the decision to develop or purchase must ultimately examine how the end result will mesh with the departmental workflow, and custom-developed solutions typically can have the greater positive impact on efficiency and productivity, substantially altering the decision balance sheet. Involving the end-users in preparation of the functional specifications is crucial to the success of the process. A large development team is not needed, and even a single programmer can develop significant solutions. Many of the risks associated with custom development can be mitigated by a well-structured development process, use of open-source tools, and embracing an agile development philosophy. In-house solutions have the significant advantage of being adaptable to changing departmental needs, contributing to efficient and higher quality patient care.

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.

Context: In 2013 the high throughput technology known as Tissue Micro Array (TMA) will be fifteen years old. Its elements (design, construction and analysis) are intuitive and the core histopathology technique is unsophisticated, which may be a reason why has eluded a rigorous scientific scrutiny. The source of errors, particularly in specimen identification and how to control for it is unreported. Formal validation of the accuracy of segmenting (also known as de-arraying) hundreds of samples, pairing with the sample data is lacking. Aims: We wanted to address these issues in order to bring the technique to recognized standards of quality in TMA use for research, diagnostics and industrial purposes. Results: We systematically addressed the sources of error and used barcode-driven data input throughout the whole process including matching the design with a TMA virtual image and segmenting that image back to individual cases, together with the associated data. In addition we demonstrate on mathematical grounds that a TMA design, when superimposed onto the corresponding whole slide image, validates on each and every sample the correspondence between the image and patient's data. Conclusions: High throughput use of the TMA technology is a safe and efficient method for research, diagnosis and industrial use if all sources of errors are identified and addressed.

Background: Last year, our pathology informatics fellowship added informatics-based interactive case studies to its existing educational platform of operational and research rotations, clinical conferences, a common core curriculum with an accompanying didactic course, and national meetings. Methods: The structure of the informatics case studies was based on the traditional business school case study format. Three different formats were used, varying in length from short, 15-minute scenarios to more formal multiple hour-long case studies. Case studies were presented over the course of three retreats (Fall 2011, Winter 2012, and Spring 2012) and involved both local and visiting faculty and fellows. Results: Both faculty and fellows found the case studies and the retreats educational, valuable, and enjoyable. From this positive feedback, we plan to incorporate the retreats in future academic years as an educational component of our fellowship program. Conclusions: Interactive case studies appear to be valuable in teaching several aspects of pathology informatics that are difficult to teach in more traditional venues (rotations and didactic class sessions). Case studies have become an important component of our fellowship's educational platform.

The Human Genome Project (HGP) provided the initial draft of mankind's DNA sequence in 2001. The HGP was produced by 23 collaborating laboratories using Sanger sequencing of mapped regions as well as shotgun sequencing techniques in a process that occupied 13 years at a cost of ~$3 billion. Today, Next Generation Sequencing (NGS) techniques represent the next phase in the evolution of DNA sequencing technology at dramatically reduced cost compared to traditional Sanger sequencing. A single laboratory today can sequence the entire human genome in a few days for a few thousand dollars in reagents and staff time. Routine whole exome or even whole genome sequencing of clinical patients is well within the realm of affordability for many academic institutions across the country. This paper reviews current sequencing technology methods and upcoming advancements in sequencing technology as well as challenges associated with data generation, data manipulation and data storage. Implementation of routine NGS data in cancer genomics is discussed along with potential pitfalls in the interpretation of the NGS data. The overarching importance of bioinformatics in the clinical implementation of NGS is emphasized. ^[7] We also review the issue of physician education which also is an important consideration for the successful implementation of NGS in the clinical workplace. NGS technologies represent a golden opportunity for the next generation of pathologists to be at the leading edge of the personalized medicine approaches coming our way. Often under-emphasized issues of data access and control as well as potential ethical implications of whole genome NGS sequencing are also discussed. Despite some challenges, it's hard not to be optimistic about the future of personalized genome sequencing and its potential impact on patient care and the advancement of knowledge of human biology and disease in the near future.

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.

Background: One of the drawbacks of studying pathology in the second year of medical school in a classroom setting is the relatively limited exposure to patient encounters/clinical rotations, making it difficult to understand and fully appreciate the significance of the course material, specifically the molecular and tissue aspects of disease. In this study, we determined if case vignettes incorporating pathologist-clinician encounters with whole slide imaging (WSI) and narrated/annotated videos of whole slide (WS) scans in addition to clinical data improved student understanding of pathologic disease processes. Materials and Methods: Case vignettes were created for several genitourinary disease processes that utilized clinical data including narratives of pathologist-clinician encounters, WSI, and annotated video tutorials of WS scans (designed to simulate "double-heading"). The students were encouraged to view the virtual slide first, with the video tutorials being provided to offer additional assistance. The case vignettes were created to be interactive with a detailed explanation of each correct and incorrect question choice. The cases were made available to all second year medical students via a website and could be viewed only after completing a 10 question pre-test. A post-test could be completed after viewing all cases followed by a brief satisfaction survey. Results: Ninety-six students completed the pre-test with an average score of 7.7/10. Fifty-seven students completed the post-test with an average score of 9.4/10. Thirty-six students completed the satisfaction survey. 94% agreed or strongly agreed that this was a useful exercise and 91% felt that it helped them better understand the topics. Conclusion: The development of interactive case vignettes incorporating simulated pathologist-clinician encounters with WSI and video tutorials of WS scans helps to improve student enthusiasm to learn and grasp pathologic aspects of disease processes that lead to clinical therapeutic decision making.

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: The need for informatics and genomics training in pathology is critical, yet limited resources for such training are available. In this study we sought to critically test the hypothesis that the incorporation of a wiki (a collaborative writing and publication tool with roots in "Web 2.0") in a combined informatics and genomics course could both (1) serve as an interactive, collaborative educational resource and reference and (2) actively engage trainees by requiring the creation and sharing of educational materials. Materials and Methods: A 2-week full-time course at our institution covering genomics, research, and pathology informatics (GRIP) was taught by 36 faculty to 18 second- and third-year pathology residents. The course content included didactic lectures and hands-on demonstrations of technology (e.g., whole-slide scanning, telepathology, and statistics software). Attendees were given pre- and posttests. Residents were trained to use wiki technology (MediaWiki) and requested to construct a wiki about the GRIP course by writing comprehensive online review articles on assigned lectures. To gauge effectiveness, pretest and posttest scores for our course were compared with scores from the previous 7 years from the predecessor course (limited to informatics) given at our institution that did not utilize wikis. Results: Residents constructed 59 peer-reviewed collaborative wiki articles. This group showed a 25% improvement (standard deviation 12%) in test scores, which was greater than the 16% delta recorded in the prior 7 years of our predecessor course (P = 0.006). Conclusions: Our use of wiki technology provided a wiki containing high-quality content that will form the basis of future pathology informatics and genomics courses and proved to be an effective teaching tool, as evidenced by the significant rise in our resident posttest scores. Data from this project provide support for the notion that active participation in content creation is an effective mechanism for mastery of content. Future residents taking this course will continue to build on this wiki, keeping content current, and thereby benefit from this collaborative teaching tool.

Background: In 2007, our healthcare system established a clinical fellowship program in Pathology Informatics. In 2010 a core didactic course was implemented to supplement the fellowship research and operational rotations. In 2011, the course was enhanced by a formal, structured core curriculum and reading list. We present and discuss our rationale and development process for the Core Curriculum and the role it plays in our Pathology Informatics Fellowship Training Program. Materials and Methods: The Core Curriculum for Pathology Informatics was developed, and is maintained, through the combined efforts of our Pathology Informatics Fellows and Faculty. The curriculum was created with a three-tiered structure, consisting of divisions, topics, and subtopics. Primary (required) and suggested readings were selected for each subtopic in the curriculum and incorporated into a curated reading list, which is reviewed and maintained on a regular basis. Results: Our Core Curriculum is composed of four major divisions, 22 topics, and 92 subtopics that cover the wide breadth of Pathology Informatics. The four major divisions include: (1) Information Fundamentals, (2) Information Systems, (3) Workflow and Process, and (4) Governance and Management. A detailed, comprehensive reading list for the curriculum is presented in the Appendix to the manuscript and contains 570 total readings (current as of March 2012). Discussion: The adoption of a formal, core curriculum in a Pathology Informatics fellowship has significant impacts on both fellowship training and the general field of Pathology Informatics itself. For a fellowship, a core curriculum defines a basic, common scope of knowledge that the fellowship expects all of its graduates will know, while at the same time enhancing and broadening the traditional fellowship experience of research and operational rotations. For the field of Pathology Informatics itself, a core curriculum defines to the outside world, including departments, companies, and health systems considering hiring a pathology informatician, the core knowledge set expected of a person trained in the field and, more fundamentally, it helps to define the scope of the field within Pathology and healthcare in general.

Background: Pathology Informatics is a new field; a field that is still defining itself even as it begins the formalization, accreditation, and board certification process. At the same time, Pathology itself is changing in a variety of ways that impact informatics, including subspecialization and an increased use of data analysis. In this paper, we examine how these changes impact both the structure of Pathology Informatics fellowship programs and the fellows' goals within those programs. Materials and Methods: As part of our regular program review process, the fellows evaluated the value and effectiveness of our existing fellowship tracks (Research Informatics, Clinical Two-year Focused Informatics, Clinical One-year Focused Informatics, and Clinical 1 + 1 Subspecialty Pathology and Informatics). They compared their education, informatics background, and anticipated career paths and analyzed them for correlations between those parameters and the fellowship track chosen. All current and past fellows of the program were actively involved with the project. Results: Fellows' anticipated career paths correlated very well with the specific tracks in the program. A small set of fellows (Clinical - one or two year - Focused Informatics tracks) anticipated clinical careers primarily focused in informatics (Director of Informatics). The majority of the fellows, however, anticipated a career practicing in a Pathology subspecialty, using their informatics training to enhance that practice (Clinical 1 + 1 Subspecialty Pathology and Informatics Track). Significantly, all fellows on this track reported they would not have considered a Clinical Two-year Focused Informatics track if it was the only track offered. The Research and the Clinical One-year Focused Informatics tracks each displayed unique value for different situations. Conclusions: It seems a "one size fits all" fellowship structure does not fit the needs of the majority of potential Pathology Informatics candidates. Increasingly, these fellowships must be able to accommodate the needs of candidates anticipating a wide range of Pathology Informatics career paths, be able to accommodate Pathology's increasingly subspecialized structure, and do this in a way that respects the multiple fellowships needed to become a subspecialty pathologist and informatician. This is further complicated as Pathology Informatics begins to look outward and takes its place in the growing, and still ill-defined, field of Clinical Informatics, a field that is not confined to just one medical specialty, to one way of practicing medicine, or to one way of providing patient care.

Context and Aims: Rapid, accurate peripheral blood differentials are essential to maintain standards of patient care. CellaVision DM96 (CellaVision AB, Lund, Sweden) (CV) is an automated digital morphology and informatics system used to locate, pre-classify, store and transmit images of platelets, red and white blood cells to a trained technologist who confirms or edits CV cell classification. We assessed our experience with CV by evaluating sensitivity, specificity, positive predictive value and negative predictive value for CV in three different patient populations. Materials and Methods: We analyzed classification accuracy of CV for white blood cells, erythroblasts, platelets and artefacts over six months for three different university hospitals using CV. Results: CV classified 211,218 events for the adult cancer center; 51,699 events for the adult general hospital; and 8,009 events for the children's hospital with accuracy of CV being 93%, 87.3% and 95.4% respectively. Sensitivity and positive predictive value were <80% for immature granulocytes (band neutrophil, promyelocyte, myelocyte and metamyelocytes) (differences usually within one stage of maturation). Cell types comprising a lower frequency of the total events, including blasts, showed lower accuracy at some sites. Conclusions: The reduced immature granulocyte classification accuracy may be due in part to the subjectivity in classification of these cells, length of experience with the system and individual expertise of the technologist. Cells with low sensitivity and positive predictive value comprised a minority of the cells and should not significantly affect the technologist re-classification time. CV serves as a clinically useful instrument in performance of peripheral blood differentials.

Context: Skype is a peer to peer software application that has been historically used for voice and video calls, instant messaging, and file transfer over the Internet. Few studies are available using Skype specifically for telepathology. Aims: Our aim is to show that dynamic nonrobotic teleconsultation is possible and even effective via means of a standard microscope camera capable of live acquisition, Skype, an established broad band internet connection, and experienced pathologists. Settings and Design: Both the consulting "sending" pathologist and consultant "receiving" pathologist are reasonably experienced general surgical pathologists at junior attending level with several years of experience in sign out. Forty-five cases were chosen encompassing a broad range of surgical pathology specimens. The cases were prospectively evaluated with the consultant diagnosis used as a preliminary pathologic impression with the final diagnosis being confirmation. Materials and Methods: Versions of Skype 5.0 and above were used along with established broadband internet connections, usually between academic medical institutions. Results: Forty of forty-five cases (89%) were essentially concordant. In four of forty-five cases (9%), the consulting impression gave a differential, but favored an entity which did not match the final diagnosis. Only one case (2%) did the consulting impression not match the final diagnosis; a discordant opinion. Conclusions: The image quality via Skype screen sharing option is excellent. Essentially no lag time was seen. We have shown in our small pilot study that Skype is an effective cost-efficient means for teleconsultation, particularly in the setting of entity-related differential diagnoses in surgical pathology and when both the consulting and consultant pathologists are reasonably experienced.

Background: Whole slide digital imaging (WSDI) offers an alternative to glass slides for diagnostic interpretation. While prior work has concentrated on the use of whole slide digital imaging for routine diagnostic cases, this study focuses on diagnostic interpretation of digital images for a highly challenging area, upper gastro-intestinal (GI) dysplasia. The aim of this study is to study the accuracy and efficiency of WSDI in the diagnosis of upper GI tract dysplasia. Materials and Methods: Forty-two hematoxylin and eosin (H and E)-stained slides representing negative, indefinite, low grade and high grade dysplasia were selected and scanned at 20x (Aperio XT). Four attending GI pathologists reviewed the WSDI, then glass slides, with at least 3-4 weeks between each media; glass slides were re-reviewed 16-18 months later. Results: Intraobserver variability for three clinically relevant categories (negative, indefinite/low grade, high grade) was wider for WSDI to glass (kappa range 0.36-0.78) than glass to glass (kappa range 0.58-0.75). In comparison to glass slide review, WSDI review required more time and was associated with an unexpected trend toward downgrading dysplasia. Conclusions: Our results suggest: (1) upper GI dysplasia can be diagnosed using WSDI with similar intraobserver reproducibility as for glass slides; however, this is not true for all pathologists; (2) pathologists may have a tendency to downgrade dysplasia in digital images; and (3) pathologists who use WSDI for interpretation of GI dysplasia cases may benefit from regular, on-going, re-review of paired digital and glass images to ensure the most accurate utilization of digital technology, at least in the early stages of implementation.

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: Conventional tissue microarrays (TMAs) consist of cores of tissue inserted into a recipient paraffin block such that a tissue section on a single glass slide can contain numerous patient samples in a spatially structured pattern. Scanning TMAs into digital slides for subsequent analysis by computer-aided diagnostic (CAD) algorithms all offers the possibility of evaluating candidate algorithms against a near-complete repertoire of variable disease morphologies. This parallel interrogation approach simplifies the evaluation, validation, and comparison of such candidate algorithms. A recently developed digital tool, digital core (dCORE), and image microarray maker (iMAM) enables the capture of uniformly sized and resolution-matched images, with these representing key morphologic features and fields of view, aggregated into a single monolithic digital image file in an array format, which we define as an image microarray (IMA). We further define the TMA-IMA construct as IMA-based images derived from whole slide images of TMAs themselves. Methods: Here we describe the first combined use of the previously described dCORE and iMAM tools, toward the goal of generating a higher-order image construct, with multiple TMA cores from multiple distinct conventional TMAs assembled as a single digital image montage. This image construct served as the basis of the carrying out of a massively parallel image analysis exercise, based on the use of the previously described spatially invariant vector quantization (SIVQ) algorithm. Results: Multicase, multifield TMA-IMAs of follicular lymphoma and follicular hyperplasia were separately rendered, using the aforementioned tools. Each of these two IMAs contained a distinct spectrum of morphologic heterogeneity with respect to both tingible body macrophage (TBM) appearance and apoptotic body morphology. SIVQ-based pattern matching, with ring vectors selected to screen for either tingible body macrophages or apoptotic bodies, was subsequently carried out on the differing TMA-IMAs, with attainment of excellent discriminant classification between the two diagnostic classes. Conclusion: The TMA-IMA construct enables and accelerates high-throughput multicase, multifield based image feature discovery and classification, thus simplifying the development, validation, and comparison of CAD algorithms in settings where the heterogeneity of diagnostic feature morphologic is a significant factor.

Objective: The opportunity to integrate clinical decision support systems into clinical practice is limited due to the lack of structured, machine readable data in the current format of the electronic health record. Natural language processing has been designed to convert free text into machine readable data. The aim of the current study was to ascertain the feasibility of using natural language processing to extract clinical information from >76,000 breast pathology reports. Approach and Procedure: Breast pathology reports from three institutions were analyzed using natural language processing software (Clearforest, Waltham, MA) to extract information on a variety of pathologic diagnoses of interest. Data tables were created from the extracted information according to date of surgery, side of surgery, and medical record number. The variety of ways in which each diagnosis could be represented was recorded, as a means of demonstrating the complexity of machine interpretation of free text. Results: There was widespread variation in how pathologists reported common pathologic diagnoses. We report, for example, 124 ways of saying invasive ductal carcinoma and 95 ways of saying invasive lobular carcinoma. There were >4000 ways of saying invasive ductal carcinoma was not present. Natural language processor sensitivity and specificity were 99.1% and 96.5% when compared to expert human coders. Conclusion: We have demonstrated how a large body of free text medical information such as seen in breast pathology reports, can be converted to a machine readable format using natural language processing, and described the inherent complexities of the task.

Pathology informatics encompasses digital imaging and related applications. Several specialized microscopy techniques have emerged which permit the acquisition of digital images ("optical biopsies") at high resolution. Coupled with fiber-optic and micro-optic components, some of these imaging techniques (e.g., optical coherence tomography) are now integrated with a wide range of imaging devices such as endoscopes, laparoscopes, catheters, and needles that enable imaging inside the body. These advanced imaging modalities have exciting diagnostic potential and introduce new opportunities in pathology. Therefore, it is important that pathology informaticists understand these advanced imaging techniques and the impact they have on pathology. This paper reviews several recently developed microscopic techniques, including diffraction-limited methods (e.g., confocal microscopy, 2-photon microscopy, 4Pi microscopy, and spatially modulated illumination microscopy) and subdiffraction techniques (e.g., photoactivated localization microscopy, stochastic optical reconstruction microscopy, and stimulated emission depletion microscopy). This article serves as a primer for pathology informaticists, highlighting the fundamentals and applications of advanced optical imaging techniques.