Hourglass, a compass navigating global and regional heterogeneity of pancreatic cancer†.

Advances in the digital pathology field have facilitated the characterization of histology samples for both clinical and preclinical research. However, uncovering subtle correlations between bioimaging, clinical and molecular parameters requires extensive statistical analysis. As a user-friendly software, Hourglass, simplifies multiparametric dataset analysis through intuitive data visualization and statistical tools. Systemic analysis of interleukin-6 (IL-6)/pStat3 signaling pathway through Hourglass revealed differences in regional immune cell composition within tumors. Moreover, these regional disparities were partially mediated by sex. Overall, Hourglass simplifies information extraction from complex datasets, resolving overlooked regional and global spatial tumor differences. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

AI-guided histopathology predicts brain metastasis in lung cancer patients.

Brain metastases can occur in nearly half of patients with early and locally advanced (stage I-III) non-small cell lung cancer (NSCLC). There are no reliable histopathologic or molecular means to identify those who are likely to develop brain metastases. We sought to determine if deep learning (DL) could be applied to routine H&E-stained primary tumor tissue sections from stage I-III NSCLC patients to predict the development of brain metastasis. Diagnostic slides from 158 patients with stage I-III NSCLC followed for at least 5 years for the development of brain metastases (Met+, 65 patients) versus no progression (Met-, 93 patients) were subjected to whole-slide imaging. Three separate iterations were performed by first selecting 118 cases (45 Met+, 73 Met-) to train and validate the DL algorithm, while 40 separate cases (20 Met+, 20 Met-) were used as the test set. The DL algorithm results were compared to a blinded review by four expert pathologists. The DL-based algorithm was able to distinguish the eventual development of brain metastases with an accuracy of 87% (p < 0.0001) compared with an average of 57.3% by the four pathologists and appears to be particularly useful in predicting brain metastases in stage I patients. The DL algorithm appears to focus on a complex set of histologic features. DL-based algorithms using routine H&E-stained slides may identify patients who are likely to develop brain metastases from those who will remain disease free over extended (>5 year) follow-up and may thus be spared systemic therapy. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Development of a multi-scanner facility for data acquisition for digital pathology artificial intelligence.

Whole slide imaging (WSI) of pathology glass slides using high-resolution scanners has enabled the large-scale application of artificial intelligence (AI) in pathology, to support the detection and diagnosis of disease, potentially increasing efficiency and accuracy in tissue diagnosis. Despite the promise of AI, it has limitations. 'Brittleness' or sensitivity to variation in inputs necessitates that large amounts of data are used for training. AI is often trained on data from different scanners but not usually by replicating the same slide across scanners. The utilisation of multiple WSI instruments to produce digital replicas of the same slides will make more comprehensive datasets and may improve the robustness and generalisability of AI algorithms as well as reduce the overall data requirements of AI training. To this end, the National Pathology Imaging Cooperative (NPIC) has built the AI FORGE (Facilitating Opportunities for Robust Generalisable data Emulation), a unique multi-scanner facility embedded in a clinical site in the NHS to (1) compare scanner performance, (2) replicate digital pathology image datasets across WSI systems, and (3) support the evaluation of clinical AI algorithms. The NPIC AI FORGE currently comprises 15 scanners from nine manufacturers. It can generate approximately 4,000 WSI images per day (approximately 7 TB of image data). This paper describes the process followed to plan and build such a facility. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma.

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Slideflow: deep learning for digital histopathology with real-time whole-slide visualization.

Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi.

Prognostic value of CDKN2A in head and neck squamous cell carcinoma via pathomics and machine learning.

This study aims to enhance the prognosis prediction of Head and Neck Squamous Cell Carcinoma (HNSCC) by employing artificial intelligence (AI) to analyse CDKN2A gene expression from pathology images, directly correlating with patient outcomes. Our approach introduces a novel AI-driven pathomics framework, delineating a more precise relationship between CDKN2A expression and survival rates compared to previous studies. Utilizing 475 HNSCC cases from the TCGA database, we stratified patients into high-risk and low-risk groups based on CDKN2A expression thresholds. Through pathomics analysis of 271 cases with available slides, we extracted 465 distinctive features to construct a Gradient Boosting Machine (GBM) model. This model was then employed to compute Pathomics scores (PS), predicting CDKN2A expression levels with validation for accuracy and pathway association analysis. Our study demonstrates a significant correlation between higher CDKN2A expression and improved median overall survival (66.73 months for high expression vs. 42.97 months for low expression, p = 0.013), establishing CDKN2A's prognostic value. The pathomic model exhibited exceptional predictive accuracy (training AUC: 0.806; validation AUC: 0.710) and identified a strong link between higher Pathomics scores and cell cycle activation pathways. Validation through tissue microarray corroborated the predictive capacity of our model. Confirming CDKN2A as a crucial prognostic marker in HNSCC, this study advances the existing literature by implementing an AI-driven pathomics analysis for gene expression evaluation. This innovative methodology offers a cost-efficient and non-invasive alternative to traditional diagnostic procedures, potentially revolutionizing personalized medicine in oncology.

Reliability and Variability of Ki-67 Digital Image Analysis Methods for Clinical Diagnostics in Breast Cancer.

Ki-67 is a nuclear protein associated with proliferation, and a strong potential biomarker in breast cancer, but is not routinely measured in current clinical management owing to a lack of standardization. Digital image analysis (DIA) is a promising technology that could allow high-throughput analysis and standardization. There is a dearth of data on the clinical reliability as well as intra- and interalgorithmic variability of different DIA methods. In this study, we scored and compared a set of breast cancer cases in which manually counted Ki-67 has already been demonstrated to have prognostic value (n = 278) to 5 DIA methods, namely Aperio ePathology (Lieca Biosystems), Definiens Tissue Studio (Definiens AG), Qupath, an unsupervised immunohistochemical color histogram algorithm, and a deep-learning pipeline piNET. The piNET system achieved high agreement (interclass correlation coefficient: 0.850) and correlation (R = 0.85) with the reference score. The Qupath algorithm exhibited a high degree of reproducibility among all rater instances (interclass correlation coefficient: 0.889). Although piNET performed well against absolute manual counts, none of the tested DIA methods classified common Ki-67 cutoffs with high agreement or reached the clinically relevant Cohen's κ of at least 0.8. The highest agreement achieved was a Cohen's κ statistic of 0.73 for cutoffs 20% and 25% by the piNET system. The main contributors to interalgorithmic variation and poor cutoff characterization included heterogeneous tumor biology, varying algorithm implementation, and setting assignments. It appears that image segmentation is the primary explanation for semiautomated intra-algorithmic variation, which involves significant manual intervention to correct. Automated pipelines, such as piNET, may be crucial in developing robust and reproducible unbiased DIA approaches to accurately quantify Ki-67 for clinical diagnosis in the future.

Advancing Artificial Intelligence Integration Into the Pathology Workflow: Exploring Opportunities in Gastrointestinal Tract Biopsies.

This review aims to present a comprehensive overview of the current landscape of artificial intelligence (AI) applications in the analysis of tubular gastrointestinal biopsies. These publications cover a spectrum of conditions, ranging from inflammatory ailments to malignancies. Moving beyond the conventional diagnosis based on hematoxylin and eosin-stained whole-slide images, the review explores additional implications of AI, including its involvement in interpreting immunohistochemical results, molecular subtyping, and the identification of cellular spatial biomarkers. Furthermore, the review examines how AI can contribute to enhancing the quality and control of diagnostic processes, introducing new workflow options, and addressing the limitations and caveats associated with current AI platforms in this context.

Comparing Accuracy of Helicobacter pylori Identification Using Traditional Hematoxylin and Eosin-Stained Glass Slides With Digital Whole Slide Imaging.

With advancements in the field of digital pathology, there has been a growing need to compare the diagnostic abilities of pathologists using digitized whole slide images against those when using traditional hematoxylin and eosin (H&E)-stained glass slides for primary diagnosis. One of the most common specimens received in pathology practices is an endoscopic gastric biopsy with a request to rule out Helicobacter pylori (H. pylori) infection. The current standard of care is the identification of the organisms on H&E-stained slides. Immunohistochemical or histochemical stains are used selectively. However, due to their small size (2-4 µm in length by 0.5-1 µm in width), visualization of the organisms can present a diagnostic challenge. The goal of the study was to compare the ability of pathologists to identify H. pylori on H&E slides using a digital platform against the gold standard of H&E glass slides using routine light microscopy. Diagnostic accuracy rates using glass slides vs digital slides were 81% vs 72% (P = .0142) based on H&E slides alone. When H. pylori immunohistochemical slides were provided, the diagnostic accuracy was significantly improved to comparable rates (96% glass vs 99% digital, P = 0.2199). Furthermore, differences in practice settings (academic/subspecialized vs community/general) and the duration of sign-out experience did not significantly impact the accuracy of detecting H. pylori on digital slides. We concluded that digital whole slide images, although amenable in different practice settings and teaching environments, does present some shortcomings in accuracy and precision, especially in certain circumstances and thus is not yet fully capable of completely replacing glass slide review for identification of H. pylori. We specifically recommend reviewing glass slides and/or performing ancillary stains, especially when there is a discrepancy between the degree of inflammation and the presence of microorganisms on digital images.

A Pipeline for Evaluation of Machine Learning/Artificial Intelligence Models to Quantify Programmed Death Ligand 1 Immunohistochemistry.

Immunohistochemistry (IHC) is used to guide treatment decisions in multiple cancer types. For treatment with checkpoint inhibitors, programmed death ligand 1 (PD-L1) IHC is used as a companion diagnostic. However, the scoring of PD-L1 is complicated by its expression in cancer and immune cells. Separation of cancer and noncancer regions is needed to calculate tumor proportion scores (TPS) of PD-L1, which is based on the percentage of PD-L1-positive cancer cells. Evaluation of PD-L1 expression requires highly experienced pathologists and is often challenging and time-consuming. Here, we used a multi-institutional cohort of 77 lung cancer cases stained centrally with the PD-L1 22C3 clone. We developed a 4-step pipeline for measuring TPS that includes the coregistration of hematoxylin and eosin, PD-L1, and negative control (NC) digital slides for exclusion of necrosis, segmentation of cancer regions, and quantification of PD-L1+ cells. As cancer segmentation is a challenging step for TPS generation, we trained DeepLab V3 in the Visiopharm software package to outline cancer regions in PD-L1 and NC images and evaluated the model performance by mean intersection over union (mIoU) against manual outlines. Only 14 cases were required to accomplish a mIoU of 0.82 for cancer segmentation in hematoxylin-stained NC cases. For PD-L1-stained slides, a model trained on PD-L1 tiles augmented by registered NC tiles achieved a mIoU of 0.79. In segmented cancer regions from whole slide images, the digital TPS achieved an accuracy of 75% against the manual TPS scores from the pathology report. Major reasons for algorithmic inaccuracies include the inclusion of immune cells in cancer outlines and poor nuclear segmentation of cancer cells. Our transparent and stepwise approach and performance metrics can be applied to any IHC assay to provide pathologists with important insights on when to apply and how to evaluate commercial automated IHC scoring systems.

A Multicenter Study Validates the WHO 2022 Classification for Conjunctival Melanocytic Intraepithelial Lesions With Clinical and Prognostic Relevance.

Several nomenclature and grading systems have been proposed for conjunctival melanocytic intraepithelial lesions (C-MIL). The fourth "WHO Classification of Eye Tumors" (WHO-EYE04) proposed a C-MIL classification, capturing the progression of noninvasive neoplastic melanocytes from low- to high-grade lesions, onto melanoma in situ (MIS), and then to invasive melanoma. This proposal was revised to the WHO-EYE05 C-MIL system, which simplified the high-grade C-MIL, whereby MIS was subsumed into high-grade C-MIL. Our aim was to validate the WHO-EYE05 C-MIL system using digitized images of C-MIL, stained with hematoxylin and eosin and immunohistochemistry. However, C-MIL cases were retrieved from 3 supraregional ocular pathology centers. Adequate conjunctival biopsies were stained with hematoxylin and eosin, Melan-A, SOX10, and PReferentially expressed Antigen in Melanoma. Digitized slides were uploaded on the SmartZoom platform and independently scored by 4 ocular pathologists to obtain a consensus score, before circulating to 14 expert eye pathologists for independent scoring. In total, 105 cases from 97 patients were evaluated. The initial consensus diagnoses using the WHO-EYE04 C-MIL system were as follows: 28 benign conjunctival melanoses, 13 low-grade C-MIL, 37 high-grade C-MIL, and 27 conjunctival MIS. Using this system resulted in 93% of the pathologists showing only fair-to-moderate agreement (kappa statistic) with the consensus score. The WHO-EYE05 C-MIL system (with high-grade C-MIL and MIS combined) improved consistency between pathologists, with the greatest level of agreement being seen with benign melanosis (74.5%) and high-grade C-MIL (85.4%). Lowest agreements remained between pathologists for low-grade C-MIL (38.7%). Regarding WHO-EYE05 C-MIL scoring and clinical outcomes, local recurrences of noninvasive lesions developed in 8% and 34% of the low- and high-grade cases. Invasive melanoma only occurred in 47% of the cases that were assessed as high-grade C-MIL. This extensive international collaborative study is the first to undertake a comprehensive review of the WHO-EYE05 C-MIL scoring system, which showed good interobserver agreement and reproducibility.

Augmented interpretation of HER2, ER, and PR in breast cancer by artificial intelligence analyzer: enhancing interobserver agreement through a reader study of 201 cases.

BACKGROUND: Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations. METHODS: AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment. RESULTS: Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance. CONCLUSIONS: This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

Blueprints from plane to space: outlook of next-generation three-dimensional histopathology.

Here, we summarize the literature relevant to recent advances in three-dimensional (3D) histopathology in relation to clinical oncology, highlighting serial sectioning, tissue clearing, light-sheet microscopy, and digital image analysis with artificial intelligence. We look forward to a future where 3D histopathology expands our understanding of human pathophysiology and improves patient care through cross-disciplinary collaboration and innovation.

Improved assessment of donor liver steatosis using Banff consensus recommendations and deep learning algorithms.

BACKGROUND & AIMS: The Banff Liver Working Group recently published consensus recommendations for steatosis assessment in donor liver biopsy, but few studies reported their use and no automated deep-learning algorithms based on the proposed criteria have been developed so far. We evaluated Banff recommendations on a large monocentric series of donor liver needle biopsies by comparing pathologists' scores with those generated by convolutional neural networks (CNNs) we specifically developed for automated steatosis assessment. METHODS: We retrospectively retrieved 292 allograft liver needle biopsies collected between January 2016 and January 2020 and performed steatosis assessment using a former intra-institution method (pre-Banff method) and the newly introduced Banff recommendations. Scores provided by pathologists and CNN models were then compared, and the degree of agreement was measured with the intraclass correlation coefficient (ICC). RESULTS: Regarding the pre-Banff method, poor agreement was observed between the pathologist and CNN models for small droplet macrovesicular steatosis (ICC: 0.38), large droplet macrovesicular steatosis (ICC: 0.08), and the final combined score (ICC: 0.16) evaluation, but none of these reached statistically significance. Interestingly, significantly improved agreement was observed using the Banff approach: ICC was 0.93 for the low-power score (p <0.001), 0.89 for the high-power score (p <0.001), and 0.93 for the final score (p <0.001). Comparing the pre-Banff method with the Banff approach on the same biopsy, pathologist and CNN model assessment showed a mean (±SD) percentage of discrepancy of 26.89 (±22.16) and 1.20 (±5.58), respectively. CONCLUSIONS: Our findings support the use of Banff recommendations in daily practice and highlight the need for a granular analysis of their effect on liver transplantation outcomes. IMPACT AND IMPLICATIONS: We developed and validated the first automated deep-learning algorithms for standardized steatosis assessment based on the Banff Liver Working Group consensus recommendations. Our algorithm provides an unbiased automated evaluation of steatosis, which will lay the groundwork for granular analysis of steatosis's short- and long-term effects on organ viability, enabling the identification of clinically relevant steatosis cut-offs for donor organ acceptance. Implementing our algorithm in daily clinical practice will allow for a more efficient and safe allocation of donor organs, improving the post-transplant outcomes of patients.

Artificial intelligence-assisted digital pathology for non-alcoholic steatohepatitis: current status and future directions.

The worldwide prevalence of non-alcoholic steatohepatitis (NASH) is increasing, causing a significant medical burden, but no approved therapeutics are currently available. NASH drug development requires histological analysis of liver biopsies by expert pathologists for trial enrolment and efficacy assessment, which can be hindered by multiple issues including sample heterogeneity, inter-reader and intra-reader variability, and ordinal scoring systems. Consequently, there is a high unmet need for accurate, reproducible, quantitative, and automated methods to assist pathologists with histological analysis to improve the precision around treatment and efficacy assessment. Digital pathology (DP) workflows in combination with artificial intelligence (AI) have been established in other areas of medicine and are being actively investigated in NASH to assist pathologists in the evaluation and scoring of NASH histology. DP/AI models can be used to automatically detect, localise, quantify, and score histological parameters and have the potential to reduce the impact of scoring variability in NASH clinical trials. This narrative review provides an overview of DP/AI tools in development for NASH, highlights key regulatory considerations, and discusses how these advances may impact the future of NASH clinical management and drug development. This should be a high priority in the NASH field, particularly to improve the development of safe and effective therapeutics.

Leveraging deep learning for detecting red blood cell morphological changes in blood films from children with severe malaria anaemia.

In sub-Saharan Africa, acute-onset severe malaria anaemia (SMA) is a critical challenge, particularly affecting children under five. The acute drop in haematocrit in SMA is thought to be driven by an increased phagocytotic pathological process in the spleen, leading to the presence of distinct red blood cells (RBCs) with altered morphological characteristics. We hypothesized that these RBCs could be detected systematically and at scale in peripheral blood films (PBFs) by harnessing the capabilities of deep learning models. Assessment of PBFs by a microscopist does not scale for this task and is subject to variability. Here we introduce a deep learning model, leveraging a weakly supervised Multiple Instance Learning framework, to Identify SMA (MILISMA) through the presence of morphologically changed RBCs. MILISMA achieved a classification accuracy of 83% (receiver operating characteristic area under the curve [AUC] of 87%; precision-recall AUC of 76%). More importantly, MILISMA's capabilities extend to identifying statistically significant morphological distinctions (p < 0.01) in RBCs descriptors. Our findings are enriched by visual analyses, which underscore the unique morphological features of SMA-affected RBCs when compared to non-SMA cells. This model aided detection and characterization of RBC alterations could enhance the understanding of SMA's pathology and refine SMA diagnostic and prognostic evaluation processes at scale.

Deep Learning-Enabled Diagnosis of Liver Adenocarcinoma.

BACKGROUND & AIMS: Diagnosis of adenocarcinoma in the liver is a frequent scenario in routine pathology and has a critical impact on clinical decision making. However, rendering a correct diagnosis can be challenging, and often requires the integration of clinical, radiologic, and immunohistochemical information. We present a deep learning model (HEPNET) to distinguish intrahepatic cholangiocarcinoma from colorectal liver metastasis, as the most frequent primary and secondary forms of liver adenocarcinoma, with clinical grade accuracy using H&E-stained whole-slide images. METHODS: HEPNET was trained on 714,589 image tiles from 456 patients who were randomly selected in a stratified manner from a pool of 571 patients who underwent surgical resection or biopsy at Heidelberg University Hospital. Model performance was evaluated on a hold-out internal test set comprising 115 patients and externally validated on 159 patients recruited at Mainz University Hospital. RESULTS: On the hold-out internal test set, HEPNET achieved an area under the receiver operating characteristic curve of 0.994 (95% CI, 0.989-1.000) and an accuracy of 96.522% (95% CI, 94.521%-98.694%) at the patient level. Validation on the external test set yielded an area under the receiver operating characteristic curve of 0.997 (95% CI, 0.995-1.000), corresponding to an accuracy of 98.113% (95% CI, 96.907%-100.000%). HEPNET surpassed the performance of 6 pathology experts with different levels of experience in a reader study of 50 patients (P = .0005), boosted the performance of resident pathologists to the level of senior pathologists, and reduced potential downstream analyses. CONCLUSIONS: We provided a ready-to-use tool with clinical grade performance that may facilitate routine pathology by rendering a definitive diagnosis and guiding ancillary testing. The incorporation of HEPNET into pathology laboratories may optimize the diagnostic workflow, complemented by test-related labor and cost savings.

Clinical evaluation of deep learning-based risk profiling in breast cancer histopathology and comparison to an established multigene assay.

PURPOSE: To evaluate the Stratipath Breast tool for image-based risk profiling and compare it with an established prognostic multigene assay for risk profiling in a real-world case series of estrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative early breast cancer patients categorized as intermediate risk based on classic clinicopathological variables and eligible for chemotherapy. METHODS: In a case series comprising 234 invasive ER-positive/HER2-negative tumors, clinicopathological data including Prosigna results and corresponding HE-stained tissue slides were retrieved. The digitized HE slides were analysed by Stratipath Breast. RESULTS: Our findings showed that the Stratipath Breast analysis identified 49.6% of the clinically intermediate tumors as low risk and 50.4% as high risk. The Prosigna assay classified 32.5%, 47.0% and 20.5% tumors as low, intermediate and high risk, respectively. Among Prosigna intermediate-risk tumors, 47.3% were stratified as Stratipath low risk and 52.7% as high risk. In addition, 89.7% of Stratipath low-risk cases were classified as Prosigna low/intermediate risk. The overall agreement between the two tests for low-risk and high-risk groups (N = 124) was 71.0%, with a Cohen's kappa of 0.42. For both risk profiling tests, grade and Ki67 differed significantly between risk groups. CONCLUSION: The results from this clinical evaluation of image-based risk stratification shows a considerable agreement to an established gene expression assay in routine breast pathology.

A Preliminary Investigation into Search and Matching for Tumor Discrimination in World Health Organization Breast Taxonomy Using Deep Networks.

Breast cancer is one of the most common cancers affecting women worldwide. It includes a group of malignant neoplasms with a variety of biological, clinical, and histopathologic characteristics. There are more than 35 different histologic forms of breast lesions that can be classified and diagnosed histologically according to cell morphology, growth, and architecture patterns. Recently, deep learning, in the field of artificial intelligence, has drawn a lot of attention for the computerized representation of medical images. Searchable digital atlases can provide pathologists with patch-matching tools, allowing them to search among evidently diagnosed and treated archival cases, a technology that may be regarded as computational second opinion. In this study, we indexed and analyzed the World Health Organization breast taxonomy (Classification of Tumors fifth ed.) spanning 35 tumor types. We visualized all tumor types using deep features extracted from a state-of-the-art deep-learning model, pretrained on millions of diagnostic histopathology images from the Cancer Genome Atlas repository. Furthermore, we tested the concept of a digital "atlas" as a reference for search and matching with rare test cases. The patch similarity search within the World Health Organization breast taxonomy data reached >88% accuracy when validating through "majority vote" and >91% accuracy when validating using top n tumor types. These results show for the first time that complex relationships among common and rare breast lesions can be investigated using an indexed digital archive.

Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study.

Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist's classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen's kappa of 0.43 but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.