Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts

We introduce a modular framework for predicting cancer-specific survival from whole slide pathology images (WSIs) that significantly improves upon the state-of-the-art accuracy. Our method integrating four key components. Firstly, to tackle large size of WSIs, we use dynamic patch selection via quantile-based thresholding for isolating prognostically informative tissue regions. Secondly, we use graph-guided k-means clustering to capture phenotype-level heterogeneity through spatial and morphological coherence. Thirdly, we use attention mechanisms that model both intra- and inter-cluster relationships to contextualize local features within global spatial relations between various types of tissue compartments. Finally, we use an expert-guided mixture density modeling for estimating complex survival distributions using Gaussian mixture models. The proposed model achieves a concordance index of 0.712 ± 0.028 and Brier score of 0.254 ± 0.018 on TCGA-KIRC (renal cancer), and a concordance index of 0.645 ± 0.017 and Brier score of 0.281 ± 0.031 on TCGA-LUAD (lung adenocarcinoma). These results are significantly better than the state-of-art and demonstrate predictive potential of the proposed method across diverse cancer types.