Search research articles

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

Lubricious anti-adhesive interface prevents friction, biofilm, and encrustation in long-term indwelling ureteral stents.

Materials today. Bio·2026

Same author

Real-World Evidence for Expanding the Criteria for Endoscopic Resection in Submucosal Gastric Cancer: The Role of Invasion Width.

Journal of gastric cancer·2026

Same author

Corrigendum to "A phase II clinical trial of paclitaxel-carboplatin as neoadjuvant therapy followed by surgery in patients with locally advanced head and neck squamous cell carcinoma" [Oral Oncol. 170 (2025) 107745].

Oral oncology·2026

Same author

Molecular and Phenotypic Characterization of Fluid-Derived Patient-Derived Cell and Organoid Models in Advanced Gastric Cancer.

Journal of gastric cancer·2026

Same author

Association of body composition and nutritional status with survival in stage IV colorectal cancer patients who underwent resection: a retrospective cohort study.

Annals of surgical treatment and research·2026

Same author

Spatial immunophenotyping of tumor-associated macrophages predicts prognostic outcomes in clear cell renal cell carcinoma.

Urologic oncology·2026

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

Search research articles

Related Experiment Video

Updated: Nov 2, 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

Yet Another Automated Gleason Grading System (YAAGGS) by weakly supervised deep learning.

Yechan Mun¹, Inyoung Paik¹, Su-Jin Shin²

¹Deep Bio Inc., Seoul, South Korea.

NPJ Digital Medicine

|June 15, 2021

Summary

A new deep learning system automates prostate cancer Gleason grading, reducing the need for expert annotations. This AI tool shows promising accuracy in predicting cancer outcomes and guiding treatment decisions.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Related Experiment Videos

Last Updated: Nov 2, 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

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Area of Science:

Computational pathology
Artificial intelligence in oncology
Digital pathology

Background:

Gleason scoring is crucial for prostate cancer prognosis and treatment selection.
Inter-observer variability in manual Gleason grading can impact patient management.
Current automated systems often require extensive expert annotations or complex algorithms.

Purpose of the Study:

To develop and validate a novel deep learning-based automated Gleason grading system for prostate needle biopsies.
To assess the system's performance without requiring extensive region-level manual annotations.
To evaluate the potential of AI in improving the consistency and accuracy of prostate cancer grading.

Main Methods:

A deep learning model was trained and validated on 6664 and 936 prostate needle biopsy slides from two institutions, respectively.
Pathological diagnoses were converted into the standardized Gleason grade groups.
The system's prediction accuracy and agreement (Cohen's kappa, quadratic-weighted kappa) were evaluated.

Main Results:

The system achieved a grade group prediction accuracy of 77.5% (κ=0.650, κ_quad=0.897) on the discovery cohort.
Cross-institutional validation yielded an accuracy of 67.4% (κ=0.553, κ_quad=0.880).
Performance comparison demonstrated the efficacy of the proposed method over baseline approaches.

Conclusions:

The developed deep learning system offers a promising approach for automated Gleason grading with reduced reliance on manual annotations.
This AI tool has the potential to improve diagnostic consistency and aid in clinical decision-making for prostate cancer.
The methodology may be adaptable for developing AI systems for other cancer diagnoses requiring less extensive annotations.