AI to help spot aggressive versus slow prostate cancer on MRI

Rad-pathomic deep learning models to assist radiologists in differentiating aggressive from indolent prostate cancer on MRI

['FUNDING_R37'] · STANFORD UNIVERSITY · NIH-11252779

This project uses artificial intelligence that links MRI images and pathology to help doctors tell aggressive prostate cancer from slow-growing or benign tissue for men facing biopsy decisions.

Quick facts

Phase['FUNDING_R37']
Study typeNih_funding
SexAll
SponsorSTANFORD UNIVERSITY (nih funded)
Locations1 site (STANFORD, UNITED STATES)
Trial IDNIH-11252779 on ClinicalTrials.gov

What this research studies

This project develops an AI that links features seen on your prostate MRI to what pathologists see under the microscope, using matched MRI and biopsy images. The team will train deep-learning models to create 'pathomic' MRI biomarkers that highlight areas more likely to be aggressive cancer. They will test the models' ability to detect cancer and to tell aggressive from indolent lesions, including when both types are present in the same lesion. The aim is to produce tools that can flag suspicious areas on MRI to guide biopsy and reduce unnecessary procedures.

Who could benefit from this research

Good fit: Men undergoing prostate MRI because of elevated PSA, abnormal exam, or who are considering a prostate biopsy would be the ideal candidates.

Not a fit: Men without a usable prostate MRI, those with MRI-incompatible implants, or people whose cancer is already fully treated and under stable management may not benefit directly.

Why it matters

Potential benefit: If successful, this could help find life-threatening prostate cancers earlier while reducing unnecessary biopsies and their side effects.

How similar studies have performed: Early work by this team and other MRI–AI studies have shown promising accuracy (AUCs around 0.85), but combining pathology-derived biomarkers with MRI to localize aggressive versus indolent disease is relatively new.

Where this research is happening

STANFORD, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.

View on NIH RePORTER →

Conditions: Atlas of Cancer Mortality in the United States

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.