XClose

UCL News

Menu

Trial to test AI for prostate MRI cancer diagnosis

5 June 2026

A new UCL-led international trial will assess whether AI can perform as well as expert radiologists at detecting prostate cancer on MRI scans.

Prostate cancer

Following the practice-changing UCL-led PROMIS and PRECISION trials, prostate MRI is now the standard first test for men with suspected prostate cancer in the UK (and many parts of the world), helping doctors avoid unnecessary invasive biopsies and detect clinically important disease earlier.

However, the rapid growth in MRI‑based diagnostic pathways, alongside a global shortage of radiologists, is placing increasing strain on healthcare systems.

With the number of prostate cancer cases expected to double globally over the next 20 years, researchers say new tools are urgently needed to ensure all men can access timely, high‑quality diagnosis.

The recent UCL-led PRIME trial has demonstrated that a quicker and cheaper MRI scan is just as accurate at diagnosing prostate cancer as the current 30–40-minute scan. This is a step towards ensuring that every man who requires an MRI scan can get one internationally.

However, interpretation of prostate MRI requires specialist expertise and has a steep learning curve, with optimal performance typically achieved by experienced genitourinary radiologists. At the same time, international projections suggest a radiologist workforce shortfall of around 40% within the next few years.

The PARADIGM trial aims to determine whether AI could help meet this growing demand without compromising diagnostic accuracy or patient safety.

Dr Alexander Ng (UCL Division of Surgery and Interventional Science), the PhD student leading the trial, said: “Prostate MRI has transformed how we diagnose prostate cancer, but access remains limited in many healthcare systems due to workforce and capacity constraints. PARADIGM is designed to test whether AI can match radiologists in detecting clinically significant cancers, using the highest level of clinical evidence.”

PARADIGM is an international, prospective, multicentre, within‑patient diagnostic study and will recruit 500 men over 18 months.

Each participant’s MRI scan will be independently interpreted by both:

  • A radiologist
  • An AI system trained to detect suspicious prostate lesions

Radiologists will initially be blinded to the AI output, allowing a direct comparison between human and AI performance. Suspicious findings identified by either reader will then be targeted for biopsy.

The primary outcome measure is the detection of clinically significant prostate cancer, defined as Gleason Grade Group 2 or higher.

The trial’s two chief investigators are Professor Veeru Kasivisvanathan (UCL Division of Surgery and Interventional Science), urological surgeon at UCLH, and Dr Doug Pendse, Honorary Associate Professor at UCL and radiologist at UCLH. They will both also be the local principal investigators at UCLH.

Professor Kasivisvanathan said: “This study is not about replacing radiologists, but about understanding how AI might be safely integrated into clinical pathways. If AI can reliably detect aggressive prostate cancer, it could help standardise care, reduce delays, and improve access to diagnosis worldwide.”

If successful, AI could:

  • Support radiologists in diagnosing prostate cancer on MRI scans
  • Help address shortages in specialist radiology expertise
  • Reduce variation in scan readings
  • Speed up diagnosis
  • Support the introduction of expanded MRI‑based screening programmes

Researchers stress that rigorous trials such as PARADIGM are essential before AI tools can be adopted into routine clinical use.

The PARADIGM trial is supported by charity funders including The John Black Charitable Foundation and Hadyn Cunningham, alongside funding from the National Institute for Health and Care Research (NIHR) and the European Association of Urology (EAU) Research Foundation.

Links

Image

Media contact

Tom Cramp

E: t.cramp@ucl.ac.uk