Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Reply to Varma et al. regarding building consensus in medicine: issues and potential solutions.

Virchows Archiv : an international journal of pathology·2026

Same author

How does AI perform compared to human expert panels in medical Delphi studies? A pilot study through the lens of pathology.

Journal of pathology informatics·2026

Same author

The impact of tissue detection on diagnostic artificial intelligence algorithms in prostate digital pathology.

Scientific reports·2026

Same author

Autophagy Plays a Suppressive Role in Bladder Tumor Formation in an Orthotopic Mouse Model and Bladder Cancer Patient Specimens.

The Kaohsiung journal of medical sciences·2026

Same author

Chemotherapy resistance of urinary bladder cancer mediated by a Notch and Wnt co-regulatory module of stemness.

Stem cells (Dayton, Ohio)·2026

Same author

Microscopic striated infarction is a feature of testicular vasculitis.

Pathology·2025

Same journal

Knowledge Gaps and Barriers to Care in Men with Postprostatectomy Incontinence: Evidence from the German ProKontinenz Trial.

European urology open science·2026

Same journal

Evolving Trends and Perioperative Outcomes of Surgical Treatment for Male Stress Urinary Incontinence: Results from the GRAND Study Register.

European urology open science·2026

Same journal

Contemporary Practices in the Assessment and Management of Climacturia: Results from an International Survey.

European urology open science·2026

Same journal

Optimization of Thulium Fiber Laser Lithotripsy Efficacy Based on Multidimensional Parameter Combination Strategies.

European urology open science·2026

Same journal

Incorporating Lower Urinary Tract Symptoms to Predict the Risk of Positive Prostate Magnetic Resonance Imaging.

European urology open science·2026

Same journal

Early Efficacy and Exploratory Biomarker Data of Bel-sar in Patients with Intermediate-risk and High-risk Non-muscle-invasive Bladder Cancer.

European urology open science·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 21, 2026

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Finding Holes: Pathologist-Level Performance Using AI for Cribriform Morphology Detection in Prostate Cancer.

Kelvin Szolnoky¹, Anders Blilie^2,3, Nita Mulliqi¹

¹Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.

European Urology Open Science

|April 20, 2026

Summary

This summary is machine-generated.

An artificial intelligence (AI) system achieved pathologist-level performance in detecting cribriform morphology in prostate cancer, improving diagnostic accuracy and potentially patient treatment. This AI tool enhances reliability and standardizes reporting for this poor-prognosis indicator.

Keywords:

Artificial intelligence Cribriform Prostate cancer

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Related Experiment Videos

Last Updated: Apr 21, 2026

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

Area of Science:

Digital pathology
Artificial intelligence in oncology
Histopathology image analysis

Background:

Cribriform morphology in prostate cancer signifies poor prognosis but is underreported.
Significant interobserver variability exists among pathologists for its detection.

Purpose of the Study:

To develop and validate an artificial intelligence (AI) system for improved cribriform pattern detection in prostate cancer.
Enhance diagnostic reliability and standardize reporting of cribriform morphology.

Main Methods:

A deep learning model (EfficientNetV2-S encoder with multiple instance learning) was developed for whole-slide classification.
The model was trained on 640 digitized prostate core needle biopsies and validated internally and externally on independent cohorts.
Performance was assessed using AUC and Cohen's κ, with comparisons against nine expert uropathologists.

Main Results:

Strong internal validation (AUC: 0.97, Cohen's κ: 0.81) and robust external validation (AUC: 0.90, Cohen's κ: 0.55) were achieved.
The AI model demonstrated superior agreement (Cohen's κ: 0.66) compared to individual pathologists (κ: 0.35–0.62).
Limitations include retrospective design and potential overestimation of performance in certain analyses.

Conclusions:

The AI model achieved pathologist-level performance in detecting cribriform morphology.
This AI approach can enhance diagnostic reliability, standardize reporting, and improve treatment decisions for prostate cancer patients.