An update on computational pathology tools for genitourinary pathology practice: A review paper from the Genitourinary Pathology Society (GUPS)

Bridging the Clinical-Computational Transparency Gap in Digital Pathology

CONTEXT.—

Computational pathology combines clinical pathology with computational analysis, aiming to enhance diagnostic capabilities and improve clinical productivity. However, communication barriers between pathologists and developers often hinder the full realization of this potential.

OBJECTIVE.—

To propose a standardized framework that improves mutual understanding of clinical objectives and computational methodologies. The goal is to enhance the development and application of computer-aided diagnostic (CAD) tools.

DESIGN.—

This article suggests pivotal roles for pathologists and computer scientists in the CAD development process. It calls for increased understanding of computational terminologies, processes, and limitations among pathologists. Similarly, it argues that computer scientists should better comprehend the true use cases of the developed algorithms to avoid clinically meaningless metrics.

RESULTS.—

CAD tools improve pathology practice significantly. Some tools have even received US Food and Drug Administration approval. However, improved understanding of machine learning models among pathologists is essential to prevent misuse and misinterpretation. There is also a need for a more accurate representation of the algorithms' performance compared to that of pathologists.

CONCLUSIONS.—

A comprehensive understanding of computational and clinical paradigms is crucial for overcoming the translational gap in computational pathology. This mutual comprehension will improve patient care through more accurate and efficient disease diagnosis.

Intermediate risk prostate tumors contain lethal subtypes

In 2024, prostate cancer (PCa) remains the most common non-skin cancer in males within the United States, with an estimated 299,010 new cases, the highest increase incident trend rate (3.8%) of all cancers, and one of the eight deadliest. PCa cases are projected to double from 1.8 million to 2.9 million per year between 2020 and 2040. According to the National Comprehensive Cancer Network (NCCN) treatment guidelines, most cases (65%) are intermediate risk (Gleason sum score <7 [3 + 4, 4 + 3], prostate organ-confined, and PSA < 20) with treatment options limited to active surveillance, external beam radiation, and/or surgery to prevent metastasis in the long term (>10 years). It is increasingly recognized that the two most common subtypes of intermediate risk PCa are cribriform architecture (CA) and intraductal carcinoma of the prostate (IDC-P), which can occur together, and both are associated with increased metastatic risk, biochemical recurrence, and disease-specific mortality. Both subtypes display hypoxia, genomic instability, and are identified as Gleason 4 in pathology reports. However, since false negatives are common (up to 50%) in these subtypes on biopsy, more research is needed to reliably detect these subtypes that have an increased risk for invasive disease. We note that even with mpMRI-guided biopsies, the sensitivity is 54% for cribriform architecture and only 37% for IDC-P. The presence of these PCa subtypes in biopsy or radical prostatectomy (RP) tissue can exclude patients from active surveillance and from designation as intermediate risk disease, further underscoring the need for increased molecular understanding of these subtypes for diagnostic purposes. Understanding the heterogeneity of intermediate risk primary PCa phenotypes, using computational pathology approaches to evaluate the fixed biopsy specimen, or video microscopy of the surgical specimen with AI-driven analysis is now achievable. New research associating the resulting phenotypes with the different therapeutic choices and vulnerabilities will likely prevent extracapsular extension, the definition of high-risk disease, and upstaging of the final pathologic stage.

Recent Advances in Genitourinary Tumors: Updates From the 5th Edition of the World Health Organization Blue Book Series

CONTEXT.—

Urinary and Male Genital Tumours is the 8th volume of the World Health Organization Classification of Tumours series, 5th edition. Released in hard copy in September 2022, it presents an update to the classification of male genital and urinary tumors in the molecular age. Building upon previous volumes in this series, significant effort has been made to harmonize terminology across organ systems for biologically similar tumors (eg, neuroendocrine tumors). Genomic terminology has been standardized and genetic syndromes covered more comprehensively. This review presents a concise summary of this volume, highlighting new entities, notable modifications relative to the 4th edition, and elements of relevance to routine clinical practice.

OBJECTIVE.—

To provide a comprehensive update on the World Health Organization classification of urinary and male genital tumors, highlighting updated diagnostic criteria and terminology.

DATA SOURCES.—

The 4th and 5th editions of the World Health Organization Classification of Tumours: Urinary and Male Genital Tumours.

CONCLUSIONS.—

The World Health Organization has made several changes in the 5th edition of the update on urinary and male genital tumors that pathologists need to be aware of for up-to-date clinical practice.

Immunohistochemical Stain-Aided Annotation Accelerates Machine Learning and Deep Learning Model Development in the Pathologic Diagnosis of Nasopharyngeal Carcinoma

Nasopharyngeal carcinoma (NPC) is an epithelial cancer originating in the nasopharynx epithelium. Nevertheless, annotating pathology slides remains a bottleneck in the development of AI-driven pathology models and applications. In the present study, we aim to demonstrate the feasibility of using immunohistochemistry (IHC) for annotation by non-pathologists and to develop an efficient model for distinguishing NPC without the time-consuming involvement of pathologists. For this study, we gathered NPC slides from 251 different patients, comprising hematoxylin and eosin (H&E) slides, pan-cytokeratin (Pan-CK) IHC slides, and Epstein-Barr virus-encoded small RNA (EBER) slides. The annotation of NPC regions in the H&E slides was carried out by a non-pathologist trainee who had access to corresponding Pan-CK IHC slides, both with and without EBER slides. The training process utilized ResNeXt, a deep neural network featuring a residual and inception architecture. In the validation set, NPC exhibited an AUC of 0.896, with a sensitivity of 0.919 and a specificity of 0.878. This study represents a significant breakthrough: the successful application of deep convolutional neural networks to identify NPC without the need for expert pathologist annotations. Our results underscore the potential of laboratory techniques to substantially reduce the workload of pathologists.