Clinical trial Recruiting at 1 site Observational Ages 40 to 90 Men only

Multi-Modal Imaging and Digital Pathology to Predict Clinically Significant Prostate Cancer

Official title: A Multicenter Study of a Deep Learning Model Based on Spatial Registration of Multimodal Imaging and Digital Pathology for Predicting Clinically Significant Prostate Cancer

Run by Guangxi Medical University · NCT07614256 · Data updated 2026-11-12

A multi-center study tests a deep learning model that combines MRI, ultrasound, and digital pathology to see if it can predict clinically significant prostate cancer non-invasively and help guide biopsies.

Quick facts

Study typeObservational
Ages40 Years to 90 Years
SexMen only
Enrollment3000 (estimated)
SponsorGuangxi Medical University
Academic / other
Drugs / interventionsradiation
Locations1 site (Liuzhou, Guangxi)
StatusRecruiting
StartedMay 30, 2025
Main results expectedJune 30, 2030
Study endsDecember 31, 2030
Registry record updatedMay 29, 2026
Trial IDNCT07614256 on ClinicalTrials.gov

Is this trial a fit for you?

Likely a good fit

Adults aged 40–90 with suspected or diagnosed prostate cancer who have undergone mpMRI and TRUS and have complete pathology data.

Probably not a fit

Patients with incomplete imaging or pathology data, prior pelvic radiation or radical prostatectomy, or contraindications to MRI may not benefit from the model.

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

This is a multicenter observational study using preoperative mpMRI, TRUS, and postoperative digital pathology to train and validate a transformer-based deep learning model. The model aims to align imaging and pathology data through biomechanically constrained spatial registration and to predict clinically significant prostate cancer while enabling risk stratification. Internal cross-validation, external verification, and public datasets will be used to assess performance, with analyses like decision curve and clinical impact curves to gauge real-world usefulness. The goal is to support more precise biopsy decisions and avoid unnecessary procedures while improving early diagnosis and treatment planning.

Why it matters

Potential benefit: If successful, the approach could reduce unnecessary biopsies and overdiagnosis while improving risk stratification and treatment decisions for prostate cancer.

How similar studies have gone: Prior work with multimodal imaging and pathology fusion has shown promise in cancer prediction, though this study adds a prospective, multicenter validation with deep learning.

Who can join: the full rules

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Subjects who are scheduled to undergo or have undergone prostate biopsy or radical prostatectomy.
2. Subjects who have completed standard-of-care preoperative multiparametric MRI (mpMRI) and transrectal ultrasound (TRUS) examinations.
3. Subjects with complete pathological diagnosis results available.
4. Age between 40 and 90 years.
5. Able and willing to provide written informed consent (for prospective cohort participants only).

Exclusion Criteria:

1. Prior history of pelvic radiation therapy or radical prostatectomy.
2. Incomplete or poor-quality mpMRI or TRUS images (e.g., motion artifacts, insufficient sequences).
3. Concurrent other primary malignant tumors.
4. Severe systemic diseases that may affect the evaluation of the prostate.
5. Subjects with incomplete clinical or pathological data.
6. Contraindications to MRI examination (e.g., incompatible metallic implants, severe claustrophobia).

Where it's running

  • Liuzhou People's Hospital Affiliated to Guangxi Medical University
    Liuzhou, Guangxi, China
    Recruiting

Study contacts

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

How to take part

  1. Review the eligibility criteria above with your treating physician.
  2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
  3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.
Last reviewed 2026-11-14 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.