Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts
This work addresses survival prediction for cancer patients from medical images, representing an incremental improvement over existing approaches.
The paper tackles predicting cancer-specific survival from whole slide pathology images by developing a modular framework that captures prognostic and morphological heterogeneity, achieving concordance indices of 0.653, 0.719, and 0.733 on TCGA datasets, surpassing state-of-the-art methods.
We propose a modular framework for predicting cancer specific survival directly from whole slide pathology images (WSIs). The framework consists of four key stages designed to capture prognostic and morphological heterogeneity. First, a Quantile Based Patch Filtering module selects prognostically informative tissue regions through quantile thresholding. Second, Graph Regularized Patch Clustering models phenotype level variations using a k nearest neighbor graph that enforces spatial and morphological coherence. Third, Hierarchical Feature Aggregation learns both intra and inter cluster dependencies to represent multiscale tumor organization. Finally, an Expert Guided Mixture Density Model estimates complex survival distributions via Gaussian mixtures, enabling fine grained risk prediction. Evaluated on TCGA LUAD, TCGA KIRC, and TCGA BRCA cohorts, our model achieves concordance indices of 0.653 ,0.719 ,and 0.733 respectively, surpassing existing state of the art approaches in survival prediction from WSIs.