Paper
HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction
Authors
Jing Dai, Chen Wu, Ming Wu, Qibin Zhang, Zexi Wu, Jingdong Zhang, Hongming Xu
Abstract
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 <a href="https://github.com/Daijing-ai/HGP-Mamba.git">this https URL</a>.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.16421v1</id>\n <title>HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk Prediction</title>\n <updated>2026-03-17T11:57:49Z</updated>\n <link href='https://arxiv.org/abs/2603.16421v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.16421v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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 <a href=\"https://github.com/Daijing-ai/HGP-Mamba.git\">this https URL</a>.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-17T11:57:49Z</published>\n <arxiv:comment>Accepted at IEEE ICME 2026. This arXiv version includes additional supplementary experiments and extended discussions beyond the conference version</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Jing Dai</name>\n </author>\n <author>\n <name>Chen Wu</name>\n </author>\n <author>\n <name>Ming Wu</name>\n </author>\n <author>\n <name>Qibin Zhang</name>\n </author>\n <author>\n <name>Zexi Wu</name>\n </author>\n <author>\n <name>Jingdong Zhang</name>\n </author>\n <author>\n <name>Hongming Xu</name>\n </author>\n </entry>"
}