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

A systematic analysis of the impact of data variation on AI-based histopathological grading of prostate cancer.

Medical image analysis·2025

Same author

Radical Prostatectomy or Watchful Waiting in Early Prostate Cancer.

The New England journal of medicine·2024

Same author

Robust, credible, and interpretable AI-based histopathological prostate cancer grading.

medRxiv : the preprint server for health sciences·2024

Same author

Lymph Node and Bone Marrow Micrometastases Define the Prognosis of Patients with pN0 Esophageal Cancer.

Cancers·2020

Same author

Upregulation of the transcription factor TFAP2D is associated with aggressive tumor phenotype in prostate cancer lacking the TMPRSS2:ERG fusion.

Molecular medicine (Cambridge, Mass.)·2020

Same author

Homogeneous MMR Deficiency Throughout the Entire Tumor Mass Occurs in a Subset of Colorectal Neuroendocrine Carcinomas.

Endocrine pathology·2020

Search research articles

Related Experiment Video

Updated: Aug 24, 2025

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Published on: October 10, 2019

AI-based prostate analysis system trained without human supervision to predict patient outcome from tissue samples.

Peter Walhagen¹, Ewert Bengtsson^1,2, Maximilian Lennartz³

¹Spearpoint Analytics AB, Stockholm, Sweden.

Journal of Pathology Informatics

|October 21, 2022

Summary

This study introduces an AI that predicts prostate cancer patient outcomes directly from tissue images, bypassing subjective Gleason grading. The AI demonstrates comparable or superior predictive accuracy to expert pathologists.

Keywords:

Artificial intelligence-based cancer grading Predicting prostate cancer recurrence Prostate cancer grading

More Related Videos

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

Related Experiment Videos

Last Updated: Aug 24, 2025

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking

Published on: October 10, 2019

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

Area of Science:

Computational pathology
Oncology
Artificial intelligence in medicine

Background:

Prostate cancer treatment planning relies on tumor aggressiveness grading using the Gleason scale, a subjective visual assessment of biopsies.
Existing AI models for Gleason grading are limited by the accuracy of the 'ground truth' human grades used for training.
There is a need for more objective and accurate methods to predict patient outcomes in prostate cancer.

Purpose of the Study:

To develop and evaluate an AI model capable of predicting prostate cancer patient outcomes directly from histopathology images.
To assess the AI model's performance independently of subjective human-derived Gleason grading.

Main Methods:

Trained an AI model using image analysis of a large biobank of prostate tissue samples with known patient outcomes.
The AI model was developed without incorporating any human knowledge of cancer grading scales.
Evaluated the AI model's predictive performance on an independent test dataset.

Main Results:

The AI model demonstrated a significant ability to predict patient outcomes directly from tissue image analysis.
The model's predictive performance was comparable to, and in some cases exceeded, that of expert pathologists using conventional Gleason grading.
This suggests a potential for AI to provide more accurate prognostic information than current subjective grading methods.

Conclusions:

Direct AI-driven outcome prediction from prostate cancer tissue images offers a promising alternative to traditional Gleason grading.
This approach may overcome limitations associated with subjective ground truth grading, leading to improved patient management.
Further validation could establish this AI as a valuable tool in precision oncology for prostate cancer.