HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction
This work addresses cancer survival prediction for medical applications by efficiently combining histology and protein data, representing a novel method for a known bottleneck in multimodal learning.
The paper tackles the challenge of predicting cancer survival risk by integrating histology images with generated protein features, addressing the high cost of protein expression profiling. It proposes HGP-Mamba, a multimodal framework that achieves state-of-the-art performance on four public cancer datasets while maintaining superior computational efficiency.
Recent advances in multimodal learning have significantly improved cancer survival risk prediction. However, the joint prognostic potential of protein markers and histopathology images remains underexplored, largely due to the high cost and limited availability of protein expression profiling. To address this challenge, we propose HGP-Mamba, a Mamba-based multimodal framework that efficiently integrates histological with generated protein features for survival risk prediction. Specifically, we introduce a protein feature extractor (PFE) that leverages pretrained foundation models to derive high-throughput protein embeddings directly from Whole Slide Images (WSIs), enabling data-efficient incorporation of molecular information. Together with histology embeddings that capture morphological patterns, we further introduce the Local Interaction-aware Mamba (LiAM) for fine-grained feature interaction and the Global Interaction-enhanced Mamba (GiEM) to promote holistic modality fusion at the slide level, thus capture complex cross-modal dependencies. Experiments on four public cancer datasets demonstrate that HGP-Mamba achieves state-of-the-art performance while maintaining superior computational efficiency compared with existing methods. Our source code is publicly available at https://github.com/Daijing-ai/HGP-Mamba.git.