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 type | Observational |
|---|---|
| Ages | 40 Years to 90 Years |
| Sex | Men only |
| Enrollment | 3000 (estimated) |
| Sponsor | Guangxi Medical University Academic / other |
| Drugs / interventions | radiation |
| Locations | 1 site (Liuzhou, Guangxi) |
| Status | Recruiting |
| Started | May 30, 2025 |
| Main results expected | June 30, 2030 |
| Study ends | December 31, 2030 |
| Registry record updated | May 29, 2026 |
| Trial ID | NCT07614256 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
- Principal investigator: Fubo Wang, MD — Guangxi Medical University
- Study coordinator: Caigou Shi, MD
- Email: shicaigou@sr.gxmu.edu.cn
- Phone: +86 13677729003
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
68Ga-XMFH01 PET/FL imaging to guide prostate cancer surgery
This study tests a new dual-modality imaging probe, 68Ga-XMFH01, to preoperatively detect prostate cancer and guide the surgeon with fluorescence during operations in adults with newly diagnosed prostate cancer.
-
Hugo Robotic Prostatectomy in an Ambulatory Surgery Center
This study tests the use of the Hugo robotic system for prostate removal in adult men treated at an outpatient surgical center.
-
Adaptive intraoperative biopsy system for prostate cancer using imaging and metabolic feedback
Aiming to test a smart biopsy approach that combines preoperative imaging with real-time metabolic signals to guide where to take prostate biopsy cores for better precision in men suspected of prostate cancer.
-
miRNA panel test to help diagnose prostate cancer
A blood test using a microRNA panel is being tested to help diagnose prostate cancer in men who are suspected of having the disease.
-
Transperineal vs Transrectal Cognitive Fusion Biopsy for Prostate Cancer
This study tests whether a transperineal cognitive fusion biopsy works as well as the traditional transrectal approach for detecting clinically significant prostate cancer in men with suspicious mpMRI findings.
-
Testing 68Ga-NYM032 PET/CT in men with newly diagnosed prostate cancer
This study tests a new PSMA-targeted PET/CT imaging agent to see if it safely and accurately locates cancer in men who have just been diagnosed with prostate cancer and are planned for surgery.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.