Prostate MRI Analysis by Radiologists and Artificial Intelligence - Disease Identification and Guided Management

NCT07647445 | Not Yet Recruiting DMC

• 1 other identifier: 338739
• Study Type: interventional
• Target: 500
• Locations: 0 countries
• Sites: N/A

Brief Summary

Prostate cancer is the most common male cancer in 112 countries and makes up 7% of global cancer cases, and is the second leading cause of cancer-related deaths in men. Normally, men with suspected prostate cancer undergo a prostate MRI, and then a Radiologist would review this scan to identify any suspicious areas for cancer within the prostate. Prostate MRI interpretation, however, is an expert skill with a steep learning curve, and internationally, there is a growing shortage of Radiologists. The PARADIGM trial aims to assess if AI can perform just as well as Radiologists in interpretating prostate MRI scans to identify prostate cancer. Enrolled participants will undergo a prostate MRI, which is the normal method used for investigating suspected prostate cancer. AI and a Radiologist will both interpret the MRI, without knowledge of each other's interpretation. Once both reports have been made, the Radiologist will be asked to produce a third, combined report. If there is a suspicious area in the prostate identified either by AI or the Radiologist, targeted biopsies will be performed. f there are no suspicious areas on the MRI and if you are at low risk of harbouring cancer, which occurs in about 30% of men, then no biopsy will be taken at all.

Conditions

Prostate CA

Keywords

MRI; Prostate; Cancer; AI; Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• Proportion of men with clinically significant cancer

  Proportion of men with clinically significant cancer detected (any pattern 4 disease on any core (i.e. Gleason Grade ≥ 3+4/Gleason grade group ≥2).

  When biopsy results available, at an expected average of 30 days post-biopsy

Secondary Outcomes (12)

• Proportion of men with clinically insignificant cancer

  When biopsy results available, at an expected average of 30 days post-biopsy

• Proportion of men with non-suspicious MRIs

  When MRI results available, at an expected average of 30 days post-MRI

• Proportion of MRIs with indeterminate scores.

  When MRI results available, at an expected average of 30 days post-MRI

• Agreement between AI and Radiologist in score of suspicion

  When MRI results available, at an expected average of 30 days post-MRI

• Diagnostic test performance characteristics (AI versus Radiologist)

  When biopsy results available, at an expected average of 30 days post-biopsy

Study Arms (2)

Radiologist interpretation of MRI +/- prostate biopsy

ACTIVE COMPARATOR

Radiologist Interpretation

Diagnostic Test: Radiologist interpretation

AI interpretation of MRI +/- prostate biopsy

EXPERIMENTAL

AI Interpretation

Diagnostic Test: AI (Lucida Pi) interpretation

Interventions

AI (Lucida Pi) interpretation DIAGNOSTIC_TEST

AI algorithm that will interpretate the prostate MRI

AI interpretation of MRI +/- prostate biopsy

Radiologist interpretation DIAGNOSTIC_TEST

Radiologist will interpret the prostate MRI (as per standard of care)

Radiologist interpretation of MRI +/- prostate biopsy

Eligibility Criteria

• Age: 18 Years+
• Sex: male
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Men at least 18 years of age referred with clinical suspicion of prostate cancer
• Serum PSA ≤ 20 ng/mL
• Fit to undergo all procedures listed in the protocol
• Able to provide written informed consent

You may not qualify if:

• Prior prostate biopsy
• Prior prostate MRI on a previous encounter\*
• Prior treatment for prostate cancer
• Contraindication to MRI (e.g. claustrophobia, pacemaker)
• Metalwork that would give rise to artefact on MRI (e.g. hip prosthesis, pelvic/spinal metalwork)
• Contraindication to prostate biopsy
• Unfit to undergo any procedures listed in protocol
• An MRI on a previous encounter means a previous prostate MRI which has been seen by a doctor and has been used to inform patient management at the time of the original MRI.

Sponsors & Collaborators

• University College, London: lead
• Lucida Medical Ltd: collaborator

MeSH Terms

Conditions

Neoplasms

Study Officials

• Veeru Kasivisvanathan, MBBS BSc FRCS MSc PGCert PhD

  Division of Surgery and Interventional Science, University College London, UK

  STUDY CHAIR

• Doug Pendse, MB ChB MD (Res) MRCS FRCR

  Department of Radiology, Universiy College London Hospitals NHS Foundation Trust, UK

  STUDY CHAIR

Central Study Contacts

Ng Alexander, MBBS BSc (Hons)

CONTACT

+44 0207 679 5057; alexander.ng@ucl.ac.uk

PARADIGM Study Team

CONTACT

med.paradigm@ucl.ac.uk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: SINGLE
• Who Masked: CARE PROVIDER
• Masking Details: AI and Radiologist interpreting the MRI for suspicion of prostate cancer are blinded to each other. After both reports are produced, they are unblinded, and a merged report is produced. All bioopsies are conducted as a result of both the AI and Radiologist interpretation, and as a result, lesions will be identified as AI and Radiologist positive, or negative, as appropriate. Diagnostic accuracy will be assessed against histology findings.
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Within-person controlled, paired cohort, diagnostic evaluation study. Participants undergo two index tests and a reference test.

Study Record Dates

• First Submitted: June 9, 2026
• First Posted: June 15, 2026
• Study Start (Estimated): October 1, 2026
• Primary Completion (Estimated): January 1, 2029
• Study Completion (Estimated): January 1, 2029
• Last Updated: June 15, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP
• Time Frame: Data will become available 1 year after publication of the main study results.
• Access Criteria: A study steering committee will review all requests for access to the data and will make decisions on whether or not to grant access to bona fide researchers based on the importance of the research question being asked, ensuring analysis is non overlapping with existing analyses and planned analyses.