MRI-based machine learning versus radiologist reads to detect prostate cancer
Official title: PRIMER (Prostate MRI With Machine LEarning vs. Radiologist) A Novel MRI-Based Machine Learning Approach vs Radiologist MRI Reading for Targeted Prostate Biopsy: A Non-Inferiority, Within-Person Randomized Controlled Trial for Prostate Cancer Detection
Run by University of Southern California · NCT07162194 · Data updated 2026-11-12
This trial tests whether MRI-based AI methods can find clinically significant prostate cancer as well as experienced radiologists in men getting a prostate biopsy or prostate removal surgery.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 20 Years and up |
| Sex | Men only |
| Enrollment | 130 (estimated) |
| Sponsor | University of Southern California Academic / other |
| Locations | 1 site (Los Angeles, California) |
| Status | Recruiting |
| Started | September 19, 2025 |
| Main results expected | October 15, 2027 |
| Study ends | October 15, 2028 |
| Registry record updated | September 1, 2026 |
| Trial ID | NCT07162194 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Men undergoing transperineal MRI/TRUS fusion prostate biopsy with a 3T multiparametric MRI within 90 days, or men undergoing radical prostatectomy with a 3T mpMRI within 180 days, who are willing to consent and attend the USC site.
✕Probably not a fit
Men with a prior history of prostate cancer, prior prostate surgery, no qualifying 3T mpMRI, or those unable to attend the USC/Norris site are not eligible and unlikely to benefit from participation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This prospective interventional study enrolls men undergoing transperineal MRI/TRUS fusion prostate biopsy (Group 1) and men undergoing radical prostatectomy or prostatectomy after biopsy (Group 2). In the biopsy cohort, patients are randomized to arms in which targeted biopsies are obtained sequentially based on standard PIRADS reads, a Green Learning (GL) AI prediction, and a Deep Learning (DL) AI prediction, alongside standard-of-care systematic cores. The primary objective is to show non-inferiority of GL AI-targeted biopsy versus PIRADS, with secondary goals including DL AI detection rates, patient-level diagnostic performance comparisons, biopsy core characteristics, predictors of clinically significant cancer, and spatial correlation with prostatectomy specimens. All participants require a 3T multiparametric prostate MRI performed within the study windows and are enrolled at the USC/Norris Comprehensive Cancer Center.
Why it matters
Potential benefit: If successful, the AI approaches could match radiologist accuracy for clinically significant prostate cancer and help standardize readings and expand access to high-quality MRI interpretation.
How similar studies have gone: Previous retrospective and some prospective reports have shown AI can approach or match experienced radiologist performance for detecting clinically significant prostate cancer on MRI, but randomized non-inferiority comparisons remain limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * PROSTATE BIOPSY COHORT: Patients undergoing transperineal MRI/TRUS fusion prostate biopsy (PBx) as per standard of care * PROSTATE BIOPSY COHORT: Patients who underwent or are undergoing 3T multiparametric MRI (T2W, diffusion weighted imaging \[DWI\], apparent diffusion coefficient \[ADC\], and dynamic contrast-enhanced \[DCE\]) within 365 days prior to biopsy * PROSTATE BIOPSY COHORT: Patients who consented to the study * RADICAL PROSTATECTOMY COHORT: Patients undergoing radical prostatectomy for primary treatment of prostate cancer as per standard of care * RADICAL PROSTATECTOMY COHORT: Patients who underwent or are undergoing 3T multiparametric MRI (T2W, DWI, ADC, and DCE) within 365 days prior to radical prostatectomy * RADICAL PROSTATECTOMY COHORT: Patients who consented to the study Exclusion Criteria: * PROSTATE BIOPSY COHORT: Patients with a history of prostate cancer * PROSTATE BIOPSY COHORT: Patients with a history of surgical treatment on benign prostate hyperplasia * PROSTATE BIOPSY COHORT: Patients undergoing saturation prostate biopsy * PROSTATE BIOPSY COHORT: Patients under 20 years old * PROSTATE BIOPSY COHORT: Patients with previous PBx history * PROSTATE BIOPSY COHORT: MRI which was not interpreted by PIRADS * PROSTATE BIOPSY COHORT: MRI with significant artifact * RADICAL PROSTATECTOMY COHORT: Patients who are undergoing neo-adjuvant hormonal therapy in conjunction with radical prostatectomy * RADICAL PROSTATECTOMY COHORT: Patients with a history of surgical treatment on benign prostate hyperplasia * RADICAL PROSTATECTOMY COHORT: Patients under 20 years old * RADICAL PROSTATECTOMY COHORT: Patients without pre-treatment MRI * RADICAL PROSTATECTOMY COHORT: MRI which was not interpreted by PIRADS * RADICAL PROSTATECTOMY COHORT: MRI with significant artifact * RADICAL PROSTATECTOMY COHORT: Patients who are included in the Biopsy cohort
Where it's running
-
USC / Norris Comprehensive Cancer Center
Los Angeles, California, United States Recruiting
Study contacts
- Principal investigator: Andre Luis Abreu, MD — University of Southern California
- Study coordinator: Ileana Aldana
- Email: Ileana.aldana@med.usc.edu
- Phone: 323-865-0702
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Understanding NK Cell Function in Prostate Cancer Across Races
This study tests whether natural killer (NK) cells behave differently in prostate cancer patients of diverse racial backgrounds by analyzing blood and tissue samples.
-
MRI or CT planning to guide high-dose-rate prostate brachytherapy
This trial tests whether adding an MRI to CT-based treatment planning for HDR prostate brachytherapy changes urinary side effects in men with localized prostate cancer.
-
Targeted Early Detection for Men at High Genetic Risk for Prostate Cancer
This study tests urinary biomarkers and PSA to see if they can improve early detection for men with a strong family or genetic risk for prostate cancer.
-
Urine and MRI approach to find aggressive prostate cancer early
This study tests whether a urine test called MPS2, paired with MRI, can better detect aggressive prostate cancer in men 50–75 at risk, possibly reducing unnecessary biopsies.
-
GET FIT Together: a socially enhanced exercise program for older men with prostate cancer
This program tests whether adding structured social support to supervised online exercise reduces cancer-related loneliness and improves mental and physical health in men 65 and older who have had prostate cancer.
-
Improved MRI methods to distinguish benign from cancerous pelvic findings
This test tries new deep-learning image-processing methods on MRI scans to get clearer images faster for adults scanned for prostate screening or suspected endometriosis.
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.