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

TL;DR

This study develops an AI model trained on prostate biopsy images to predict biochemical recurrence after prostatectomy, demonstrating moderate accuracy and improved prognostic stratification when combined with clinical data.

Contribution

The paper introduces a novel AI-based approach using foundation models and attention-based learning to predict BCR from biopsy samples, with validation across multiple external cohorts.

Findings

AI model achieved 5-year AUCs of 0.64-0.70 across cohorts

Combining clinical data improved risk stratification

AI added prognostic value over existing guidelines

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.