AI-based Prediction of Biochemical Recurrence from Biopsy and Prostatectomy Samples

2026-01-28

AI Summary

Current methods struggle to accurately predict the risk of biochemical recurrence (BCR) following radical prostatectomy. This study proposes a multi-instance learning framework based on preoperative biopsy histopathology slides, integrating foundation models with attention mechanisms. It demonstrates for the first time that an AI model trained exclusively on biopsy images can effectively predict postoperative BCR across different specimen types—biopsy and resection—achieving 5-year time-dependent AUCs of 0.64, 0.70, and 0.70 in three external cohorts (LEOPARD, CHIMERA, and TCGA-PRAD), outperforming the conventional CAPRA-S score. Furthermore, integrating clinical variables with the model significantly enhances risk stratification and improves postoperative prognostic assessment.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Biochemical recurrence (BCR) after radical prostatectomy (RP) is a surrogate marker for aggressive prostate cancer with adverse outcomes, yet current prognostic tools remain imprecise. We trained an AI-based model on diagnostic prostate biopsy slides from the STHLM3 cohort (n = 676) to predict patient-specific risk of BCR, using foundation models and attention-based multiple instance learning. Generalizability was assessed across three external RP cohorts: LEOPARD (n = 508), CHIMERA (n = 95), and TCGA-PRAD (n = 379). The image-based approach achieved 5-year time-dependent AUCs of 0.64, 0.70, and 0.70, respectively. Integrating clinical variables added complementary prognostic value and enabled statistically significant risk stratification. Compared with guideline-based CAPRA-S, AI incrementally improved postoperative prognostication. These findings suggest biopsy-trained histopathology AI can generalize across specimen types to support preoperative and postoperative decision making, but the added value of AI-based multimodal approaches over simpler predictive models should be critically scrutinized in further studies.

Problem

• biochemical recurrence
• prostate cancer
• prognostic tools
• radical prostatectomy
• risk prediction

Innovation

• foundation models
• attention-based multiple instance learning
• biochemical recurrence prediction
• histopathology AI
• multimodal prognostication