Multicenter Assessment of AI-Based Risk Stratification for Identifying Clinically Relevant Prostate Cancer via Biparametric MRI
By
Karsten Guenzel
Maarten G. Poirot
Almar van Loon
Emanuele Messina
Martina Pecoraro
Valeria Panebianco
Robert Princenthal
Francesco Giganti
September 26, 2026
Clinical Scorecard: Multicenter Assessment of AI-Based Risk Stratification for Identifying Clinically Relevant Prostate Cancer via Biparametric MRI
At a Glance
Category Detail
Condition Clinically significant prostate cancer (csPCa) Key Mechanisms Utilization of biparametric MRI and AI for risk stratification and detection Target Population Men aged ≥ 18 years undergoing prostate MRI followed by biopsy or prostatectomy Care Setting Multicenter diagnostic accuracy study
Key Highlights
AI-based risk classification compared with radiologist-assigned PI-RADS for csPCa detection Study involved three cohorts from Germany, the Netherlands, and the United States Histopathology served as the reference standard for csPCa detection AI tools provide Low, Medium, or High-risk classifications for lesions PI-RADS categories consolidated into three operational groups for clinical practice Guideline-Based Recommendations
Diagnosis
Use of PI-RADS for prostate mpMRI interpretation AI-assisted biopsy triage for equivocal lesions categorized as PI-RADS 3 Management
Targeted and systematic biopsy protocols based on MRI findings Monitoring & Follow-up
Regular assessment of biopsy outcomes and imaging results Risks
Inter-reader variability in PI-RADS scoring, particularly for PI-RADS 3 Patient & Prescribing Data
Men with suspected clinically significant prostate cancer
AI-derived risk scores can guide biopsy decisions and reduce unnecessary procedures
Clinical Best Practices
Incorporate AI tools for enhanced detection and risk stratification in prostate MRI Standardize reporting protocols across institutions to minimize variability Utilize a multidisciplinary approach for managing prostate cancer diagnosis and treatment Related Resources & Content
