MurreNet: Modeling Holistic Multimodal Interactions Between Histopathology and Genomic Profiles for Survival Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909677409796096 |
|---|---|
| author | Liu, Mingxin Cai, Chengfei Li, Jun Xu, Pengbo Li, Jinze Ma, Jiquan Xu, Jun |
| author_facet | Liu, Mingxin Cai, Chengfei Li, Jun Xu, Pengbo Li, Jinze Ma, Jiquan Xu, Jun |
| contents | Cancer survival prediction requires integrating pathological Whole Slide Images (WSIs) and genomic profiles, a challenging task due to the inherent heterogeneity and the complexity of modeling both inter- and intra-modality interactions. Current methods often employ straightforward fusion strategies for multimodal feature integration, failing to comprehensively capture modality-specific and modality-common interactions, resulting in a limited understanding of multimodal correlations and suboptimal predictive performance. To mitigate these limitations, this paper presents a Multimodal Representation Decoupling Network (MurreNet) to advance cancer survival analysis. Specifically, we first propose a Multimodal Representation Decomposition (MRD) module to explicitly decompose paired input data into modality-specific and modality-shared representations, thereby reducing redundancy between modalities. Furthermore, the disentangled representations are further refined then updated through a novel training regularization strategy that imposes constraints on distributional similarity, difference, and representativeness of modality features. Finally, the augmented multimodal features are integrated into a joint representation via proposed Deep Holistic Orthogonal Fusion (DHOF) strategy. Extensive experiments conducted on six TCGA cancer cohorts demonstrate that our MurreNet achieves state-of-the-art (SOTA) performance in survival prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MurreNet: Modeling Holistic Multimodal Interactions Between Histopathology and Genomic Profiles for Survival Prediction Liu, Mingxin Cai, Chengfei Li, Jun Xu, Pengbo Li, Jinze Ma, Jiquan Xu, Jun Image and Video Processing Computer Vision and Pattern Recognition Cancer survival prediction requires integrating pathological Whole Slide Images (WSIs) and genomic profiles, a challenging task due to the inherent heterogeneity and the complexity of modeling both inter- and intra-modality interactions. Current methods often employ straightforward fusion strategies for multimodal feature integration, failing to comprehensively capture modality-specific and modality-common interactions, resulting in a limited understanding of multimodal correlations and suboptimal predictive performance. To mitigate these limitations, this paper presents a Multimodal Representation Decoupling Network (MurreNet) to advance cancer survival analysis. Specifically, we first propose a Multimodal Representation Decomposition (MRD) module to explicitly decompose paired input data into modality-specific and modality-shared representations, thereby reducing redundancy between modalities. Furthermore, the disentangled representations are further refined then updated through a novel training regularization strategy that imposes constraints on distributional similarity, difference, and representativeness of modality features. Finally, the augmented multimodal features are integrated into a joint representation via proposed Deep Holistic Orthogonal Fusion (DHOF) strategy. Extensive experiments conducted on six TCGA cancer cohorts demonstrate that our MurreNet achieves state-of-the-art (SOTA) performance in survival prediction. |
| title | MurreNet: Modeling Holistic Multimodal Interactions Between Histopathology and Genomic Profiles for Survival Prediction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04891 |