A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement

Abstract Cancer survival prediction, as a critical task in clinical prognosis analysis, holds significant importance for guiding treatment decisions and patient management. This paper proposes a survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement (MSHG-...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaofeng Yang, Yongjie Liang, Fan Qin, Yulong Cao, Peiyuan Wang, Jiaying Fan, Bizhong Wei
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Journal of King Saud University: Computer and Information Sciences
Subjects:
Online Access:https://doi.org/10.1007/s44443-025-00202-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225865422962688
author Chaofeng Yang
Yongjie Liang
Fan Qin
Yulong Cao
Peiyuan Wang
Jiaying Fan
Bizhong Wei
author_facet Chaofeng Yang
Yongjie Liang
Fan Qin
Yulong Cao
Peiyuan Wang
Jiaying Fan
Bizhong Wei
author_sort Chaofeng Yang
collection DOAJ
description Abstract Cancer survival prediction, as a critical task in clinical prognosis analysis, holds significant importance for guiding treatment decisions and patient management. This paper proposes a survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement (MSHG-CMR), which achieves deep joint modeling and efficient information fusion of pathological images and multi-omics data by integrating multi-scale hypergraph enhancement and cross-modal refinement Transformer technology. In the method design, the hypergraph construction module captures high-order feature associations of pathological images at different resolutions and effectively aligns feature distributions across scales through homomorphic nonlinear mapping; subsequently, the cross-modal refinement Transformer module based on rotary encoding achieves dynamic information transfer and complementary refinement between visual features and multi-omics data through attention mechanisms and position decay designs; finally, a feature fusion attention mechanism is introduced to fuse multi-modal features, which both suppresses inter-modal redundancy and effectively mitigates information conflicts, thereby enhancing the precision of individualized prognosis analysis. Experimental results show that MSHG-CMR improves the C-index performance by 1.7% overall compared to existing SOTA methods on the TCGA-BLCA dataset and by 1.1% on the TCGA-LUAD dataset, demonstrating its generalizability across different cancer types. Code is available at: https://github.com/MUYI-XIAN/MSHG-CMR .
format Article
id doaj-art-bc2bff0fcc9e4e7e83575ad6e31413be
institution Kabale University
issn 1319-1578
2213-1248
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Journal of King Saud University: Computer and Information Sciences
spelling doaj-art-bc2bff0fcc9e4e7e83575ad6e31413be2025-08-24T11:53:38ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782213-12482025-08-0137711810.1007/s44443-025-00202-3A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinementChaofeng Yang0Yongjie Liang1Fan Qin2Yulong Cao3Peiyuan Wang4Jiaying Fan5Bizhong Wei6School of Computer Science and Information Security, Guilin University of Electronic TechnologyLife Science Institute, Guangxi Medical UniversitySchool of Computer Science and Information Security, Guilin University of Electronic TechnologySchool of Computer Science and Information Security, Guilin University of Electronic TechnologySchool of Computer Science and Information Security, Guilin University of Electronic TechnologySchool of Computer Science and Information Security, Guilin University of Electronic TechnologySchool of Computer Science and Information Security, Guilin University of Electronic TechnologyAbstract Cancer survival prediction, as a critical task in clinical prognosis analysis, holds significant importance for guiding treatment decisions and patient management. This paper proposes a survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement (MSHG-CMR), which achieves deep joint modeling and efficient information fusion of pathological images and multi-omics data by integrating multi-scale hypergraph enhancement and cross-modal refinement Transformer technology. In the method design, the hypergraph construction module captures high-order feature associations of pathological images at different resolutions and effectively aligns feature distributions across scales through homomorphic nonlinear mapping; subsequently, the cross-modal refinement Transformer module based on rotary encoding achieves dynamic information transfer and complementary refinement between visual features and multi-omics data through attention mechanisms and position decay designs; finally, a feature fusion attention mechanism is introduced to fuse multi-modal features, which both suppresses inter-modal redundancy and effectively mitigates information conflicts, thereby enhancing the precision of individualized prognosis analysis. Experimental results show that MSHG-CMR improves the C-index performance by 1.7% overall compared to existing SOTA methods on the TCGA-BLCA dataset and by 1.1% on the TCGA-LUAD dataset, demonstrating its generalizability across different cancer types. Code is available at: https://github.com/MUYI-XIAN/MSHG-CMR .https://doi.org/10.1007/s44443-025-00202-3Multi-modal learningHypergraph enhancementSurvival prediction
spellingShingle Chaofeng Yang
Yongjie Liang
Fan Qin
Yulong Cao
Peiyuan Wang
Jiaying Fan
Bizhong Wei
A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
Journal of King Saud University: Computer and Information Sciences
Multi-modal learning
Hypergraph enhancement
Survival prediction
title A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
title_full A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
title_fullStr A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
title_full_unstemmed A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
title_short A survival prediction network based on multi-scale hypergraph enhancement and cross-modal refinement
title_sort survival prediction network based on multi scale hypergraph enhancement and cross modal refinement
topic Multi-modal learning
Hypergraph enhancement
Survival prediction
url https://doi.org/10.1007/s44443-025-00202-3
work_keys_str_mv AT chaofengyang asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT yongjieliang asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT fanqin asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT yulongcao asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT peiyuanwang asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT jiayingfan asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT bizhongwei asurvivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT chaofengyang survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT yongjieliang survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT fanqin survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT yulongcao survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT peiyuanwang survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT jiayingfan survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement
AT bizhongwei survivalpredictionnetworkbasedonmultiscalehypergraphenhancementandcrossmodalrefinement