A whole-slide foundation model for digital pathology from real-world data.

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles1-3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context4. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet5 method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data6. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision-language pretraining for pathology7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.

Pseudo-class part prototype networks for interpretable breast cancer classification.

Interpretability in machine learning has become increasingly important as machine learning is being used in more and more applications, including those with high-stakes consequences such as healthcare where Interpretability has been regarded as a key to the successful adoption of machine learning models. However, using confounding/irrelevant information in making predictions by deep learning models, even the interpretable ones, poses critical challenges to their clinical acceptance. That has recently drawn researchers' attention to issues beyond the mere interpretation of deep learning models. In this paper, we first investigate application of an inherently interpretable prototype-based architecture, known as ProtoPNet, for breast cancer classification in digital pathology and highlight its shortcomings in this application. Then, we propose a new method that uses more medically relevant information and makes more accurate and interpretable predictions. Our method leverages the clustering concept and implicitly increases the number of classes in the training dataset. The proposed method learns more relevant prototypes without any pixel-level annotated data. To have a more holistic assessment, in addition to classification accuracy, we define a new metric for assessing the degree of interpretability based on the comments of a group of skilled pathologists. Experimental results on the BreakHis dataset show that the proposed method effectively improves the classification accuracy and interpretability by respectively 8 % and 18 % . Therefore, the proposed method can be seen as a step toward implementing interpretable deep learning models for the detection of breast cancer using histopathology images.

Digital dermatopathology implementation: Experience at a multisite academic institution.

BACKGROUND: Technology has revolutionized not only direct patient care but also diagnostic care processes. This study evaluates the transition from glass-slide microscopy to digital pathology (DP) at a multisite academic institution, using mixed methods to understand user perceptions of digitization and key productivity metrics of practice change. METHODS: Participants included dermatopathologists, pathology reporting specialists, and clinicians. Electronic surveys and individual or group interviews included questions related to technology comfort, trust in DP, and rationale for DP adoption. Case volumes and turnaround times were abstracted from the electronic health record from Qtr 4 2020 to Qtr 1 2023 (inclusive). Data were analyzed descriptively, while interviews were analyzed using methods of content analysis. RESULTS: Thirty-four staff completed surveys and 22 participated in an interview. Case volumes and diagnostic turnaround time did not differ across the institution during or after implementation timelines (p = 0.084; p = 0.133, respectively). 82.5% (28/34) of staff agreed that DP improved the sign-out experience, with accessibility, ergonomics, and annotation features described as key factors. Clinicians reported positive perspectives of DP impact on patient safety and interdisciplinary collaboration. CONCLUSIONS: Our study demonstrates that DP has a high acceptance rate, does not adversely impact productivity, and may improve patient safety and care collaboration.

Transforming diagnostics: The implementation of digital pathology in clinical laboratories.

Digital pathology (DP) has emerged as a cutting-edge technology that promises to revolutionise diagnostics in clinical laboratories. This perspective article explores the implementation planning and considerations of DP in a single multicentre institution in Canada, the University Health Network, discussing benefits, challenges, potential implications and considerations for future adopters. We examine the transition from traditional microscopy to digital slide scanning and its impact on pathology practice, patient care and medical research. Furthermore, we address the regulatory, infrastructure and change management considerations for successful integration into clinical laboratories. By highlighting the advantages and addressing concerns, we aim to shed light on the transformative potential of DP and its role in shaping the future of diagnostics.

Principles of Analytic Validation of Immunohistochemical Assays: Guideline Update.

CONTEXT.­: In 2014, the College of American Pathologists developed an evidence-based guideline to address analytic validation of immunohistochemical assays. Fourteen recommendations were offered. Per the National Academy of Medicine standards for developing trustworthy guidelines, guidelines should be updated when new evidence suggests modifications. OBJECTIVE.­: To assess evidence published since the release of the original guideline and develop updated evidence-based recommendations. DESIGN.­: The College of American Pathologists convened an expert panel to perform a systematic review of the literature and update the original guideline recommendations using the Grading of Recommendations Assessment, Development and Evaluation approach. RESULTS.­: Two strong recommendations, 1 conditional recommendation, and 12 good practice statements are offered in this updated guideline. They address analytic validation or verification of predictive and nonpredictive assays, and recommended revalidation procedures following changes in assay conditions. CONCLUSIONS.­: While many of the original guideline statements remain similar, new recommendations address analytic validation of assays with distinct scoring systems, such as programmed death receptor-1 and analytic verification of US Food and Drug Administration approved/cleared assays; more specific guidance is offered for validating immunohistochemistry performed on cytology specimens.

Histopathologic evaluation of gastric intestinal metaplasia in non-neoplastic biopsy specimens: Accuracy and interobserver reliability among general pathologists and pathology residents.

OBJECTIVES: This study aimed to evaluate the accuracy and interobserver reliability of diagnosing and subtyping gastric intestinal metaplasia (IM) among general pathologists and pathology residents at a university hospital in Thailand, focusing on the challenges in the histopathologic evaluation of gastric IM for less experienced practitioners. METHODS: The study analyzed 44 non-neoplastic gastric biopsies, using a consensus diagnosis of gastrointestinal pathologists as the reference standard. Participants included 6 general pathologists and 9 pathology residents who assessed gastric IM and categorized its subtype (complete, incomplete, or mixed) on digital slides. After initial evaluations and receiving feedback, participants reviewed specific images of gastric IM, as agreed by experts. Following a one-month washout period, a reevaluation of the slides was conducted. RESULTS: Diagnostic accuracy, interobserver reliability, and time taken for diagnosis improved following training, with general pathologists showing higher accuracies than residents (median accuracy of gastric IM detection: 100 % vs. 97.7 %). Increased years of experience were associated with more IM detection accuracy (p-value<0.05). However, the overall median accuracy for diagnosing incomplete IM remained lower than for complete IM (86.4 % vs. 97.7 %). After training, diagnostic errors occurred in 6 out of 44 specimens (13.6 %), reported by over 40 % of participants. Errors involved omitting 5 slides with incomplete IM and 1 with complete IM, all showing a subtle presence of IM. CONCLUSIONS: The study highlights the diagnostic challenges in identifying incomplete gastric IM, showing notable discrepancies in accuracy and interobserver agreement. It underscores the need for better diagnostic protocols and training to enhance detection and management outcomes.

Digital odyssey: lessons learnt from a reverse transition from a digital to a manual pathology workflow.

In the fully digital Caltagirone pathology laboratory, a reverse shift from a digital to a manual workflow occurred due to a server outage in September 2023. Here, insights gained from this unplanned transition are explored. Surveying the affected pathologists and technicians revealed unanimous preferences for the time-saving and error-reducing capabilities of the digital methodology. Conversely, the return to manual methods highlighted increased dissatisfaction and reduced efficiency, emphasising the superiority of digital workflows. This case study underscores that transition challenges are not inherent to digital workflows but to transitioning itself, advocating for the adoption of digital technologies in all pathology practices.

Digital pathology for reporting histopathology samples, including cancer screening samples - definitive evidence from a multisite study.

AIMS: To conduct a definitive multicentre comparison of digital pathology (DP) with light microscopy (LM) for reporting histopathology slides including breast and bowel cancer screening samples. METHODS: A total of 2024 cases (608 breast, 607 GI, 609 skin, 200 renal) were studied, including 207 breast and 250 bowel cancer screening samples. Cases were examined by four pathologists (16 study pathologists across the four speciality groups), using both LM and DP, with the order randomly assigned and 6 weeks between viewings. Reports were compared for clinical management concordance (CMC), meaning identical diagnoses plus differences which do not affect patient management. Percentage CMCs were computed using logistic regression models with crossed random-effects terms for case and pathologist. The obtained percentage CMCs were referenced to 98.3% calculated from previous studies. RESULTS: For all cases LM versus DP comparisons showed the CMC rates were 99.95% [95% confidence interval (CI) = 99.90-99.97] and 98.96 (95% CI = 98.42-99.32) for cancer screening samples. In speciality groups CMC for LM versus DP showed: breast 99.40% (99.06-99.62) overall and 96.27% (94.63-97.43) for cancer screening samples; [gastrointestinal (GI) = 99.96% (99.89-99.99)] overall and 99.93% (99.68-99.98) for bowel cancer screening samples; skin 99.99% (99.92-100.0); renal 99.99% (99.57-100.0). Analysis of clinically significant differences revealed discrepancies in areas where interobserver variability is known to be high, in reads performed with both modalities and without apparent trends to either. CONCLUSIONS: Comparing LM and DP CMC, overall rates exceed the reference 98.3%, providing compelling evidence that pathologists provide equivalent results for both routine and cancer screening samples irrespective of the modality used.

Mesothelioma in the pleura, pericardium and peritoneum: Recommendations from the International Collaboration on Cancer Reporting (ICCR).

AIMS: Mesothelioma is a rare malignancy of the serosal membranes that is commonly related to exposure to asbestos. Despite extensive research and clinical trials, prognosis to date remains poor. Consistent, comprehensive and reproducible pathology reporting form the basis of all future interventions for an individual patient, but also ensures that meaningful data are collected to identify predictive and prognostic markers. METHODS AND RESULTS: This article details the International Collaboration on Cancer Reporting (ICCR) process and the development of the international consensus mesothelioma reporting data set. It describes the 'core' and 'non-core' elements to be included in pathology reports for mesothelioma of all sites, inclusive of clinical, macroscopic, microscopic and ancillary testing considerations. An international expert panel consisting of pathologists and a medical oncologist produced a set of data items for biopsy and resection specimens based on a critical review and discussion of current evidence, and in light of the changes in the 2021 WHO Classification of Tumours. The commentary focuses particularly upon new entities such as mesothelioma in situ and provides background on relevant and essential ancillary testing as well as implementation of the new requirement for tumour grading. CONCLUSION: We recommend widespread and consistent implementation of this data set, which will facilitate accurate reporting and enhance the consistency of data collection, improve the comparison of epidemiological data, support retrospective research and ultimately help to improve clinical outcomes. To this end, all data sets are freely available worldwide on the ICCR website (www.iccr-cancer.org/data-sets).

Swiss digital pathology recommendations: results from a Delphi process conducted by the Swiss Digital Pathology Consortium of the Swiss Society of Pathology.

Integration of digital pathology (DP) into clinical diagnostic workflows is increasingly receiving attention as new hardware and software become available. To facilitate the adoption of DP, the Swiss Digital Pathology Consortium (SDiPath) organized a Delphi process to produce a series of recommendations for DP integration within Swiss clinical environments. This process saw the creation of 4 working groups, focusing on the various components of a DP system (1) scanners, quality assurance and validation of scans, (2) integration of Whole Slide Image (WSI)-scanners and DP systems into the Pathology Laboratory Information System, (3) digital workflow-compliance with general quality guidelines, and (4) image analysis (IA)/artificial intelligence (AI), with topic experts for each recruited for discussion and statement generation. The work product of the Delphi process is 83 consensus statements presented here, forming the basis for "SDiPath Recommendations for Digital Pathology". They represent an up-to-date resource for national and international hospitals, researchers, device manufacturers, algorithm developers, and all supporting fields, with the intent of providing expectations and best practices to help ensure safe and efficient DP usage.

Digital image analysis and artificial intelligence in pathology diagnostics-the Swiss view.

Digital pathology (DP) is increasingly entering routine clinical pathology diagnostics. As digitization of the routine caseload advances, implementation of digital image analysis algorithms and artificial intelligence tools becomes not only attainable, but also desirable in daily sign out. The Swiss Digital Pathology Consortium (SDiPath) has initiated a Delphi process to generate best-practice recommendations for various phases of the process of digitization in pathology for the local Swiss environment, encompassing the following four topics: i) scanners, quality assurance, and validation of scans; ii) integration of scanners and systems into the pathology laboratory information system; iii) the digital workflow; and iv) digital image analysis (DIA)/artificial intelligence (AI). The current article focuses on the DIA-/AI-related recommendations generated and agreed upon by the working group and further verified by the Delphi process among the members of SDiPath. Importantly, they include the view and the currently perceived needs of practicing pathologists from multiple academic and cantonal hospitals as well as private practices.

Quality Management System in Clinical Digital Pathology Operations at a Tertiary Cancer Center.

Digital pathology workflows can improve pathology operations by allowing reliable and fast retrieval of digital images, digitally reviewing pathology slides, enabling remote work and telepathology, use of computer-aided tools, and sharing of digital images for research and educational purposes. The need for quality systems is a prerequisite for successful clinical-grade digital pathology adoption and patient safety. In this article, we describe the development of a structured digital pathology laboratory quality management system (QMS) for clinical digital pathology operations at Memorial Sloan Kettering Cancer Center (MSK). This digital pathology-specific QMS development stemmed from the gaps that were identified when MSK integrated digital pathology into its clinical practice. The digital scan team in conjunction with the Department of Pathology and Laboratory Medicine quality team developed a QMS tailored to the scanning operation to support departmental and institutional needs. As a first step, systemic mapping of the digital pathology operations identified the prescan, scan, and postscan processes; instrumentation; and staffing involved in the digital pathology operation. Next, gaps identified in quality control and quality assurance measures led to the development of standard operating procedures and training material for the different roles and workflows in the process. All digital pathology-related documents were subject to regulatory review and approval by departmental leadership. The quality essentials were developed into an extensive Digital Pathology Quality Essentials framework to specifically address the needs of the growing clinical use of digital pathology technologies. Using the unique digital experience gained at MSK, we present our recommendations for QMS for large-scale digital pathology operations in clinical settings.

SGCL: Spatial guided contrastive learning on whole-slide pathological images.

Self-supervised representation learning (SSL) has achieved remarkable success in its application to natural images while falling behind in performance when applied to whole-slide pathological images (WSIs). This is because the inherent characteristics of WSIs in terms of gigapixel resolution and multiple objects in training patches are fundamentally different from natural images. Directly transferring the state-of-the-art (SOTA) SSL methods designed for natural images to WSIs will inevitably compromise their performance. We present a novel scheme SGCL: Spatial Guided Contrastive Learning, to fully explore the inherent properties of WSIs, leveraging the spatial proximity and multi-object priors for stable self-supervision. Beyond the self-invariance of instance discrimination, we expand and propagate the spatial proximity for the intra-invariance from the same WSI and inter-invariance from different WSIs, as well as propose the spatial-guided multi-cropping for inner-invariance within patches. To adaptively explore such spatial information without supervision, we propose a new loss function and conduct a theoretical analysis to validate it. This novel scheme of SGCL is able to achieve additional improvements over the SOTA pre-training methods on diverse downstream tasks across multiple datasets. Extensive ablation studies have been carried out and visualizations of these results have been presented to aid understanding of the proposed SGCL scheme. As open science, all codes and pre-trained models are available at https://github.com/HHHedo/SGCL.

Standardized Clinical Annotation of Digital Histopathology Slides at the Point of Diagnosis.

As digital pathology replaces conventional glass slide microscopy as a means of reporting cellular pathology samples, the annotation of digital pathology whole slide images is rapidly becoming part of a pathologist's regular practice. Currently, there is no recognizable organization of these annotations, and as a result, pathologists adopt an arbitrary approach to defining regions of interest, leading to irregularity and inconsistency and limiting the downstream efficient use of this valuable effort. In this study, we propose a Standardized Annotation Reporting Style for digital whole slide images. We formed a list of 167 commonly annotated entities (under 12 specialty subcategories) based on review of Royal College of Pathologists and College of American Pathologists documents, feedback from reporting pathologists in our NHS department, and experience in developing annotation dictionaries for PathLAKE research projects. Each entity was assigned a suitable annotation shape, SNOMED CT (SNOMED International) code, and unique color. Additionally, as an example of how the approach could be expanded to specific tumor types, all lung tumors in the fifth World Health Organization of thoracic tumors 2021 were included. The proposed standardization of annotations increases their utility, making them identifiable at low power and searchable across and between cases. This would aid pathologists reporting and reviewing cases and enable annotations to be used for research. This structured approach could serve as the basis for an industry standard and be easily adopted to ensure maximum functionality and efficiency in the use of annotations made during routine clinical examination of digital slides.

Integrating cytology into routine digital pathology workflow: a 5-year journey.

Despite recent advances in digital imaging, the adoption of digital cytology is challenging due to technical limitations. This study describes our 5-year institutional experience with the implementation of digital cytology. The routine cytology workflow included conventional two-step screening by cytotechnologists, followed by sign out by pathologists. We introduced sign out of cytologic cases using a microscopic digital imaging platform operated by cytotechnologists, which allowed for remote review of slides by cytopathologists via video streaming. We also provided cytologic correlation to support the virtual slide-based sign out of histopathological specimens and for a weekly pathology-radiology conference. In addition, positive cytology cases were archived for integration into the laboratory information system and for prospective computational pathology studies. We also summarized lessons learned over the years and outlined our vision for future developments. This unique experience may serve as a role model for other institutions.

The international system for reporting serous fluid cytopathology: The initial project survey.

OBJECTIVE: An international panel in the field of body fluid cytology, supported by the International Academy of Cytology and the American Society of Cytopathology, conducted a survey to identify opinions and explore existing practice patterns regarding body fluid cytopathology. METHODS: The study group, formed during the 2018 European Congress of Cytology in Madrid, generated a survey of 54 questions related to the practice and taxonomy of body fluid cytology. The survey was available online from 28 August 2018 until 10 December 2018. Participants were invited through the websites and listserves of the professional societies. RESULTS: The survey collected 593 international participant responses. Questions pertained to practice patterns and diagnostic language. Information was collected regarding credentials, work setting, work volume (4-10,000 samples) and years in practice (0-60 years). The responses revealed variations in diagnostic practice and sample management. Direct smears and ThinPrep® preparations are the most popular methods, followed by Cytospin® and SurePath®. Most (70%) respondents perform ancillary studies on their material, with over 50% preferring a cell block preparation. Approximately 32% indicated that they are capable of performing genetic studies on the samples. Nearly 78% of participants would accept a two-stage cytology report, with a preliminary assessment followed by a final diagnosis that accounts for ancillary studies to generate a more precise cytological interpretation. Approximately one-third (36%) never report adequacy on body fluid samples. Most (78%) report a general category result (negative, atypical, suspicious, or positive) and 22% provide a detailed surgical pathology type report. Most (73.6%) participants believe that both Papanicolaou stains and a modified Giemsa stain (eg Diff Quik) should be standard preparations for all serous fluid cytology. CONCLUSIONS: The results of the survey demonstrated strong support for the development of a unified system for reporting body fluid cytopathology among respondents.