Development of a Risk Calculator for Clinically Significant Prostate Cancer Using Biparametric MRI Deep Learning and Clinical Parameters

Motivation: Early detection of clinically significant prostate cancer (csPCa) through AI models may reduce unnecessary biopsies and improve screening efficiency. Goal(s): This study aims to establish and evaluate a csPCa risk calculator by combining a deep learning artificial intelligence model based on biparametric magnetic resonance imaging (bp-MRI) with clinical parameters. Approach: A deep learning model based on bp-MRI was used to predict Gleason score ranges (Artificial intelligence-Gleason Score, AI-GS), and was combined with clinical indices to create a csPCa risk calculator. Results: The established csPCa risk calculator demonstrated excellent screening capabilities through multicenter studies， outperforming traditional screening methods Impact: The developed risk calculator offers valuable insights for personalized treatment strategies and enhances prognosis evaluation in clinical practice. Its utilization can lead to more targeted biopsies, reducing unnecessary procedures and improving patient care.