Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images

TL;DR

This paper presents a novel computational framework for survival prediction from whole-slide histopathology images, integrating spatially-aware patch selection, clustering, hierarchical attention, and a flexible survival model, achieving state-of-the-art results.

Contribution

It introduces four innovative methods to address spatial heterogeneity and complex survival distributions in WSIs, advancing personalized cancer prognosis.

Findings

Achieved state-of-the-art concordance indices on TCGA cohorts

Improved calibration and interpretability of survival predictions

Outperformed existing histology-only and multimodal models

Abstract

Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational pathology framework that addresses these limitations through four complementary innovations: (1) Quantile-Gated Patch Selection for dynamically identifying prognostically relevant regions, (2) Graph-Guided Clustering to group patches by spatial and morphological similarity, (3) Hierarchical Context Attention to model both local tissue interactions and global slide-level context, and (4) an Expert-Driven Mixture of Log-Logistics module that flexibly models complex survival distributions. Across large TCGA cohorts, our method achieves state-of-the-art performance, yielding time-dependent concordance indices of 0.644 on LUAD, 0.751 on KIRC, and 0.752 on BRCA, consistently outperforming both histology-only and multimodal baselines. The framework further provides improved calibration and interpretability, advancing the use of WSIs for personalized cancer prognosis.