TRACE-PCa: Predicting Prostate Cancer Progression from Longitudinal MRI During Active Surveillance
For prostate cancer patients on active surveillance, this model offers a non-invasive method to predict progression, potentially reducing unnecessary biopsies.
TRACE-PCa predicts prostate cancer progression during active surveillance from longitudinal MRI without requiring lesion segmentation, using a temporal attention gate and multimodal fusion. It outperforms baselines and matches radiologist performance, achieving higher positive predictive value while maintaining high negative predictive value, potentially reducing unnecessary biopsies.
Active surveillance (AS) is the preferred strategy for favorable-risk prostate cancer, yet current protocols rely on scheduled repeat biopsies, most of which reveal no progression and are unnecessary. Existing risk-stratification tools operate on single time-point imaging or depend on explicit lesion segmentation, limiting their ability to capture longitudinal change and excluding patients without an MRI-visible lesion. In this study, we propose an end-to-end temporal and multimodal model for predicting pathological progression during AS without lesion segmentation. We encode each serial scan with a pretrained 3D MRI foundation model and introduce a temporal attention gate that recalibrates the multi-visit features to amplify focal imaging changes associated with progression. The gated imaging representation is then fused with clinical variables in a multimodal framework to estimate the probability of progression. Validated on a longitudinal AS cohort, our approach consistently outperforms competing baselines and performs comparably to the radiologist assessment representing current clinical practice. It maintains high negative predictive value while achieving higher positive predictive value, demonstrating its potential to safely reduce unnecessary biopsies during surveillance.