DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction

Pathology whole-slide images (WSIs) are widely used for cancer survival analysis because of their comprehensive histopathological information at both cellular and tissue levels, enabling quantitative, large-scale, and prognostically rich tumor feature analysis. However, most existing methods in WSI survival analysis struggle with limited interpretability and often overlook predictive uncertainty in heterogeneous slide images. In this paper, we propose DPsurv, a dual-prototype whole-slide image evidential fusion network that outputs uncertainty-aware survival intervals, while enabling interpretation of predictions through patch prototype assignment maps, component prototypes, and component-wise relative risk aggregation. Experiments on five publicly available datasets achieve the highest mean concordance index and the lowest mean integrated Brier score, validating the effectiveness and reliability of DPsurv. The interpretation of prediction results provides transparency at the feature, reasoning, and decision levels, thereby enhancing the trustworthiness and interpretability of DPsurv. Survival analysis, which predicts survival probabilities and outcomes over time, is a critical task in oncology for guiding therapeutic decision-making and improving patient outcomes. As a direct reflection of tumor progression, whole-slide images (WSIs) have recently emerged as an essential source of information for survival prediction in computational pathology (Zhang et al., 2025). The major challenges for identifying reliable prognostic patterns from WSIs lie in the gigapixel scale and the tissue heterogeneity (Wang et al., 2022; Xu et al., 2024). Failing to model and address these challenges can result in incomplete risk assessments, leading to suboptimal treatment planning and potentially compromised survival outcomes (Liu et al., 2025b; Shi et al., 2024b).