Prostate-Specific Foundation Models for Enhanced Detection of Clinically Significant

2025-02-01

AI Summary

To address low clinical specificity and high false-positive rates in prostate cancer diagnosis—leading to unnecessary biopsies—this study proposes ProViCNet, a prostate-specific vision foundation model. Methodologically, we introduce the first biopsy-guided, organ-level cross-modal (mpMRI/TRUS) contrastive learning framework, integrated with PSA fusion and multi-center federated learning across six hospitals (4,401 cases); we further design the ProViCNet-PSA virtual screening protocol. Key contributions include: mpMRI-based detection AUCs of 0.875–0.966, significantly outperforming radiologists (0.907 vs. 0.805, *p* < 0.001); and virtual screening increasing specificity from 15% to 38% (*p* < 0.001), substantially reducing unnecessary biopsies. ProViCNet is the first cross-modal foundation model specifically designed for clinically significant prostate cancer, validated against histopathologically confirmed biopsy as the ground-truth standard.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Accurate prostate cancer diagnosis remains challenging. Even when using MRI, radiologists exhibit low specificity and significant inter-observer variability, leading to potential delays or inaccuracies in identifying clinically significant cancers. This leads to numerous unnecessary biopsies and risks of missing clinically significant cancers. Here we present prostate vision contrastive network (ProViCNet), prostate organ-specific vision foundation models for Magnetic Resonance Imaging (MRI) and Trans-Rectal Ultrasound imaging (TRUS) for comprehensive cancer detection. ProViCNet was trained and validated using 4,401 patients across six institutions, as a prostate cancer detection model on radiology images relying on patch-level contrastive learning guided by biopsy confirmed radiologist annotations. ProViCNet demonstrated consistent performance across multiple internal and external validation cohorts with area under the receiver operating curve values ranging from 0.875 to 0.966, significantly outperforming radiologists in the reader study (0.907 versus 0.805, p<0.001) for mpMRI, while achieving 0.670 to 0.740 for TRUS. We also integrated ProViCNet with standard PSA to develop a virtual screening test, and we showed that we can maintain the high sensitivity for detecting clinically significant cancers while more than doubling specificity from 15% to 38% (p<0.001), thereby substantially reducing unnecessary biopsies. These findings highlight that ProViCNet's potential for enhancing prostate cancer diagnosis accuracy and reduce unnecessary biopsies, thereby optimizing diagnostic pathways.

Problem

• Prostate Cancer
• Diagnostic Accuracy
• Unnecessary Surgery

Innovation

• ProViCNet
• MRI-TRUS Fusion
• Virtual Screening Test