Comprehensive Survival Prediction by Integrating Multi-grained Multi-modal Interactions

The core message of this article is that by leveraging the inherent hierarchical structure of whole slide images (WSIs) and transcriptomic data, and efficiently modeling intra-modal and inter-modal interactions at different granularity levels, the proposed SurvMamba framework can achieve superior performance in survival prediction compared to existing state-of-the-art methods, while also being computationally more efficient.