Introduction: The coronavirus disease 2019 (COVID-19) pandemic has increased the use of technology for communication including departmental conferences, working remotely, and distance teaching. Methods to enable these activities should be developed and promulgated. Objective: To repurpose a preexisting educational website to enable the development of a COVID-19 autopsy biorepository to support distance teaching and COVID-19 research. Methods: After consent was obtained, autopsies were performed on patients with a confirmed positive severe acute respiratory syndrome coronavirus-2 reverse-transcriptase-polymerase-chain reaction test. Autopsies were performed according to a COVID-19 protocol, and all patients underwent both gross and microscopic examination. The H and E histology slides were scanned using a Leica Biosystems Aperio CS ScanScope whole slide scanner and the digital slide files were converted to deep zoom images that could be uploaded to the University of Alabama at Birmingham (UAB) Pathology Educational Instructional Resource website where virtual microscopy of the slides is available. Results: A total of 551 autopsy slides from 24 UAB COVID-19 cases, 1 influenza H1N1 case and 1 tuberculosis case were scanned and uploaded. Five separate COVID-19 research teams used the digital slides remotely with or without a pathologist on a Zoom call. The scanned slides were used to produce one published case report and one published research project. The digital COVID-19 autopsy biorepository was routinely used for educational conferences and research meetings locally, nationally and internationally. Conclusion: The repurposing of a pre-existing website enabled telepathology consultation for research and education purposes. Combined with other communication technology (Zoom) this achievement highlights what is possible using pre-existing technologies during a global pandemic.

The COVID-19 pandemic presented numerous challenges to the continuity of programmed cell death ligand 1 (PD-L1) assay training events conducted by our organization. Under typical conditions, these training events are face-to-face affairs, where participants are trained to assay algorithms on glass slides during multi-headed scope sessions. Social distancing measures undertaken to slow pandemic spread necessitated the adaptation of our training methods to facilitate assay training and subsequent continuation of clinical trials. The present report details the creation and use of the Roche pathology training portal (PTP) that allowed for remote training to diagnostic assay algorithms. The PTP is a web-based system comprised of a learning management system (LMS) coupled to an image management system (IMS). Whole slide images (WSIs) were produced using a DP200 instrument (Roche, Pleasanton, CA) and these scan files were then uploaded to an IMS. Courses were created on the LMS using annotated WSIs that were shared with enrolled pathologists worldwide during assay training events. These courses culminated in assay certification examinations, where pathologists evaluated test-case WSIs and evaluated these cases within the LMS. Trainee submissions were analyzed for pass/fail status by comparing user data entries with consensus scores on these test-case WSIs. To date, 47 pathologist trainings have occurred and of these, 44 have successfully passed the associated assay certification exam on the first attempt (93% 1^st-try pass rate). The PTP allowed roche to continue training sites during the COVID-19 pandemic, and these early results demonstrate the capability of this digital solution regarding PD-L1 diagnostic assay training events.

Purpose: Validating artificial intelligence algorithms for clinical use in medical images is a challenging endeavor due to a lack of standard reference data (ground truth). This topic typically occupies a small portion of the discussion in research papers since most of the efforts are focused on developing novel algorithms. In this work, we present a collaboration to create a validation dataset of pathologist annotations for algorithms that process whole slide images. We focus on data collection and evaluation of algorithm performance in the context of estimating the density of stromal tumor-infiltrating lymphocytes (sTILs) in breast cancer. Methods: We digitized 64 glass slides of hematoxylin- and eosin-stained invasive ductal carcinoma core biopsies prepared at a single clinical site. A collaborating pathologist selected 10 regions of interest (ROIs) per slide for evaluation. We created training materials and workflows to crowdsource pathologist image annotations on two modes: an optical microscope and two digital platforms. The microscope platform allows the same ROIs to be evaluated in both modes. The workflows collect the ROI type, a decision on whether the ROI is appropriate for estimating the density of sTILs, and if appropriate, the sTIL density value for that ROI. Results: In total, 19 pathologists made 1645 ROI evaluations during a data collection event and the following 2 weeks. The pilot study yielded an abundant number of cases with nominal sTIL infiltration. Furthermore, we found that the sTIL densities are correlated within a case, and there is notable pathologist variability. Consequently, we outline plans to improve our ROI and case sampling methods. We also outline statistical methods to account for ROI correlations within a case and pathologist variability when validating an algorithm. Conclusion: We have built workflows for efficient data collection and tested them in a pilot study. As we prepare for pivotal studies, we will investigate methods to use the dataset as an external validation tool for algorithms. We will also consider what it will take for the dataset to be fit for a regulatory purpose: study size, patient population, and pathologist training and qualifications. To this end, we will elicit feedback from the Food and Drug Administration via the Medical Device Development Tool program and from the broader digital pathology and AI community. Ultimately, we intend to share the dataset, statistical methods, and lessons learned.

Background: In the setting of kidney transplantation, histopathology of kidney biopsies is a key element in the organ assessment and allocation. Despite the broad diffusion of the Remuzzi–Karpinski score on preimplantation kidney biopsies, scientific evidence of its correlation to the transplantation outcome is controversial. The main issues affecting the prognostic value of histopathology are the referral to general on-call pathologists and the semiquantitative feature of the score, which can raise issues of interpretation. Digital pathology has shown very reliable and effective in the oncological diagnosis and treatment; however, the spread of such technologies is lagging behind in the field of transplantation. The aim of our study was to create a digital online platform where whole-slide images (WSI) of preimplantation kidney biopsies could be uploaded and stored. Methods: We included 210 kidney biopsies collected between January 2015 and December 2019 from the joint collaboration of the transplantation centers of Padua and Verona. The selected slides, stained with hematoxylin and eosin, were digitized and uploaded on a shared web platform. For each case, the on-call pathologists' Remuzzi grades were obtained from the original report, together with the clinical data and the posttransplantation follow-up. Results: The storage of WSI of preimplantation kidney biopsies would have several clinical, scientific, and educational advantages. The clinical utility relies on the possibility to consult online expert pathologists and real-time quality checks of diagnosis. From the perspective of follow-up, the archived digitized biopsies can offer a useful comparison to posttransplantation biopsies. In addition, the digital online platform is a precious tool for multidisciplinary meetings aimed both at the clinical discussion and at the design of research projects. Furthermore, this archive of readily available WSI is an important educational resource for the training of professionals. Conclusions: Finally, the web platform lays the foundation for the introduction of artificial intelligence in the field of transplantation that would help create new diagnostic algorithms and tools with the final aim of increasing the precision of organ assessment and its predictive value for transplant outcome.

Background: The implementation of a fully digital workflow in any anatomic pathology department requires a complete conversion to a tracked system. Ensuring the strict correspondence of the material submitted for the analysis, from the accessioning to the reporting phase, is mandatory in the anatomic pathology laboratory, especially when implementing the digital pathology for primary histological diagnosis. The proposed solutions, up to now, rely on the verification that all the materials present in the glass slide are also present in the whole slide images (WSIs). Although different methods have already been implemented for this purpose (e.g., the “macroimage” of the digital slide, representing the overview of the glass slide), the recent introduction of a device to capture the cut surface of paraffin blocks put the quality control of the digital workflow a step forward, allowing to match the digitized slide with the corresponding block. This system may represent a reliable, easy-to-use alternative to further reduce tissue inconsistencies between material sent to the lab and the final glass slides or WSIs. Methods: The Anatomic Pathology of the Gravina Hospital in Caltagirone, Sicily, Italy, has implemented the application of the BlocDoc devices (SPOT Imaging, Sterling Heights, USA) in its digital workflow. The instruments were positioned next to every microtome/sectioning station, with the possibility to capture the “normal” and the polarized image of the cut surface of the blocks directly by the technician. The presence of a monitor in the BlocDoc device allowed the technician to check the concordance between the cut surface of the block and the material on the corresponding slide. The link between BlocDoc and the laboratory information system, through the presence of the 2D barcode, allowed the pathologists to access the captured image of the cut surface of the block at the pathologist workstation, thus enabling the direct comparison between this image and the WSI (thumbnail and “macroimage”). Results: During the implementation period, more than 10.000 (11.248) blocks were routinely captured using the BlocDoc. The employment of this approach allowed a drastic reduction of the discordances and tissue inconsistencies. The implementation of the BlocDoc in the routine allowed the detection of two different types of “errors,” the so-called “systematic” and “occasional” ones. The first type was intrinsic of some specific specimens (e.g., transurethral resection of the prostate, nasal polypectomies, and piecemeal uterine myomectomies) characterized by the three-dimensional nature of the fragments and affected almost 100% of these samples. On the other hand, the “occasional” errors, mainly due to inexperience or extreme caution of the technicians in handling tiny specimens, affected 98 blocks (0.9%) of these samples and progressively reduced with the rising confidence with the BlocDoc. One of these cases was clinically relevant. No problems in the recognition of the 2D barcodes were encountered using a laser cassette printer. Finally, rare failures have been recorded during the period, accounting for <0.1% of all the cases, mainly due to network connection issues. Conclusions: The implementation of BlocDoc can further improve the effectiveness of the digital workflow, demonstrating its safety and robustness as a valid alternative to the traditional, nontracked analogic workflow.

Background: Adoption of the Digital Imaging and Communications in Medicine (DICOM) standard for whole slide images (WSIs) has been slow, despite significant time and effort by standards curators. One reason for the lack of adoption is that there are few tools which exist that can meet the requirements of WSIs, given an evolving ecosystem of best practices for implementation. Eventually, vendors will conform to the specification to ensure enterprise interoperability, but what about archived slides? Millions of slides have been scanned in various proprietary formats, many with examples of rare histologies. Our hypothesis is that if users and developers had access to easy to use tools for migrating proprietary formats to the open DICOM standard, then more tools would be developed as DICOM first implementations. Methods: The technology we present here is dicom_wsi, a Python based toolkit for converting any slide capable of being read by the OpenSlide library into DICOM conformant and validated implementations. Moreover, additional postprocessing such as background removal, digital transformations (e.g., ink removal), and annotation storage are also described. dicom_wsi is a free and open source implementation that anyone can use or modify to meet their specific purposes. Results: We compare the output of dicom_wsi to two other existing implementations of WSI to DICOM converters and also validate the images using DICOM capable image viewers. Conclusion: dicom_wsi represents the first step in a long process of DICOM adoption for WSI. It is the first open source implementation released in the developer friendly Python programming language and can be freely downloaded at https:// github.com/Steven N Hart/dicom_wsi.

Background: Remote reporting in anatomic pathology is an important advantage of digital pathology that has not been much explored. The COVID-19 pandemic has provided an opportunity to explore this important application of digital pathology system in a tertiary care cancer center to ensure patient care and staff safety. Regulatory guidelines have been described for remote reporting following the pandemic. Herein, we describe our experience of validation of digital pathology workflow for remote reporting to encourage pathologists to utilize this facility which opens door for multiple, multidisciplinary collaborations. Objective: To demonstrate the validation and the operational feasibility of remote reporting using a digital pathology system. Materials and Methods: Our retrospective validation included whole-slide images (WSIs) of 60 cases of histopathology and 20 cases each of frozen sections and a digital image-based breast algorithm after a washout period of 3 months. Three pathologists with different models of consumer-grade laptops reviewed the cases remotely to assess the diagnostic concordance and operational feasibility of the modified workflow. The slides were digitized on a USFDA-approved Philips UFS 300 scanner at ×40 resolution (0.25 μm/pixel) and viewed on the Image Management System through a web browser. All the essential parameters were reported for each case. After successful validation, 886 cases were reported remotely from March 29, 2020, to June 30, 2020, prospectively. Light microscopy formed the gold standard reference in remote reporting. Results: 100% major diagnostic concordance was observed in the validation of remote reporting in the retrospective and prospective studies using consumer-grade laptops. The deferral rate was 0.34%. 97.6% of histopathology and 100% of frozen sections were signed out within the turnaround time. Network speed and a lack of virtual private network did not significantly affect the study. Conclusion: This study of validation and reporting of complete pathology cases remotely, including their operational feasibility during a public health emergency, proves that remote sign-out using a digital pathology system is not inferior to WSIs on medical-grade monitors and light microscopy. Such studies on remote reporting open the door for the use of digital pathology for interinstitutional consultation and collaboration: Its main intended use.

Background: Hematology analysis comprises some of the highest volume tests run in clinical laboratories. Autoverification of hematology results using computer-based rules reduces turnaround time for many specimens, while strategically targeting specimen review by technologist or pathologist. Methods: Autoverification rules had been developed over a decade at an 800-bed tertiary/quarternary care academic medical central laboratory serving both adult and pediatric populations. In the process of migrating to newer hematology instruments, we analyzed the rates of the autoverification rules/flags most commonly associated with triggering manual review. We were particularly interested in rules that on their own often led to manual review in the absence of other flags. Prior to the study, autoverification rates were 87.8% (out of 16,073 orders) for complete blood count (CBC) if ordered as a panel and 85.8% (out of 1,940 orders) for CBC components ordered individually (not as the panel). Results: Detailed analysis of rules/flags that frequently triggered indicated that the immature granulocyte (IG) flag (an instrument parameter) and rules that reflexed platelet by impedance method (PLT-I) to platelet by fluorescent method (PLT-F) represented the two biggest opportunities to increase autoverification. The IG flag threshold had previously been validated at 2%, a setting that resulted in this flag alone preventing autoverification in 6.0% of all samples. The IG flag threshold was raised to 5% after detailed chart review; this was also the instrument vendor's default recommendation for the newer hematology analyzers. Analysis also supported switching to PLT-F for all platelet analysis. Autoverification rates increased to 93.5% (out of 91,692 orders) for CBC as a panel and 89.8% (out of 11,982 orders) for individual components after changes in rules and laboratory practice. Conclusions: Detailed analysis of autoverification of hematology testing at an academic medical center clinical laboratory that had been using a set of autoverification rules for over a decade revealed opportunities to optimize the parameters. The data analysis was challenging and time-consuming, highlighting opportunities for improvement in software tools that allow for more rapid and routine evaluation of autoverification parameters.

Background: Morphologic rare cell detection is a laborious, operator-dependent process which has the potential to be improved by the use of image analysis using artificial intelligence. Detection of rare hemoglobin H (HbH) inclusions in red cells in the peripheral blood is a common screening method for alpha-thalassemia. This study aims to develop a convolutional neural network-based algorithm for the detection of HbH inclusions. Methods: Digital images of HbH-positive and HbH-negative blood smears were used to train and test the software. The software performance was tested on images obtained at various magnifications and on different scanning platforms. Another model was developed for total red cell counting and was used to confirm HbH cell frequency in alpha-thalassemia trait. The threshold minimum red cells to image for analysis was determined by Poisson modeling and validated on image sets. Results: The sensitivity and specificity of the software for HbH+ cells on images obtained at ×100, ×60, and ×40 objectives were close to 91% and 99%, respectively. When an AI-aided diagnostic model was tested on a pilot of 40 whole slide images (WSIs), good inter-rater reliability and high sensitivity and specificity of slide-level classification were obtained. Using the lowest frequency of HbH+ cells (1 in 100,000) observed in our study, we estimated that a minimum of 2.4 × 106 red cells would need to be analyzed to reduce misclassification at the slide level. The minimum required smear size was validated on 78 image sets which confirmed its validity. Conclusions: WSI image analysis can be utilized effectively for morphologic rare cell detection. The software can be further developed on WISs and evaluated in future clinical validation studies comparing AI-aided diagnosis with the routine diagnostic method.

Background: Digital pathology has been increasingly implemented for primary surgical pathology diagnosis. In our institution, digital pathology was recently deployed in the gynecologic (GYN) pathology practice. A notable challenge encountered in the digital evaluation of GYN specimens was high rates of scanning failure of specimens with fragmented as well as scant tissue. To improve tissue detection failure rates, we implemented a novel use of the collodion bag cell block preparation method. Materials and Methods: In this study, we reviewed 108 endocervical curettage (ECC) specimens, representing specimens processed with and without the collodion bag cell block method (n = 56 without collodion bag, n = 52 with collodion bag). Results: Tissue detection failure rates were reduced from 77% (43/56) in noncollodion bag cases to 23/52 (44%) of collodion bag cases, representing a 42% reduction. The median total area of tissue detection failure per level was 0.35 mm² (interquartile range [IQR]: 0.14, 0.70 mm²) for noncollodion bag cases and 0.08 mm² (IQR: 0.03, 0.20 mm²) for collodion bag cases. This represents a greater than fourfold reduction in the total area of tissue detection failure per level (P < 0.001). In addition, there were no out-of-focus levels among collodion bag cases, compared to 6/56 (11%) of noncollodion bag cases (median total area = 4.9 mm²). Conclusions: The collodion bag method significantly improved the digital image quality of fragmented/scant GYN curettage specimens, increased efficiency and accuracy of diagnostic evaluation, and enhanced identification of tissue contamination during processing. The logistical challenges and labor cost of deploying the collodion bag protocol are important considerations for feasibility assessment at an institutional level.