A Magnetic Resonance Imaging-Based Prediction Model for Prostate Biopsy Risk Stratification

Area of Science:

• Urology
• Radiology
• Oncology

Background:

• Multiparametric magnetic resonance imaging (MRI) and fusion-guided biopsies enhance prostate cancer detection.
• The added value of MRI in prediction models beyond clinical parameters remains unclear.

Purpose of the Study:

• To evaluate if an MRI-based prediction model can decrease unnecessary prostate cancer biopsies.
• To assess the diagnostic performance of MRI in risk stratification for prostate cancer.

Main Methods:

• A prediction model incorporating MRI-derived parameters and clinical variables was developed and validated.
• Patients underwent MRI, MRI-transrectal ultrasound (TRUS) fusion-guided biopsy, and systematic biopsy.
• Receiver operating characteristic curve and decision curve analyses were performed.

Main Results:

• The MRI model significantly improved the area under the curve from 64% to 84% in the validation cohort.
• At a 20% risk threshold, the MRI model demonstrated a lower false-positive rate (46%) compared to the baseline model (92%).
• The MRI model could potentially reduce biopsies by 18 per 100 patients without increasing missed clinically significant prostate cancers.

Conclusions:

• Integrating MRI-derived parameters into risk models can reduce unnecessary prostate cancer biopsies.
• This approach maintains a high diagnostic rate for clinically significant prostate cancers, improving patient management.