aiqbench analysis
MIST introduces a novel architecture for multimodal survival prediction by using genomic tokens to query histology context derived from foundation models, addressing challenges in external cohort generalization. This approach effectively fuses whole-slide images and genomic profiles across multiple cancer types, offering a compact strategy that outperforms standard fusion baselines without merging modalities only at the final stage.
MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention
arXiv:2609.21811v1 Announce Type: new Abstract: Multimodal survival models can combine complementary prognostic information from whole-slide images and genomic profiles, but effective fusion remains challenging amid external cohort shift and computational complexity. To address these challenges, we propose MIST, multimodal survival prediction with genomic-guided histology attention. MIST represents genomic features as tokens and allows them to query compact foundation-model-derived histology context tokens before survival prediction. This design enriches molecular information with histology context rather than merging separately encoded modalities only at the final stage. Training combines discrete-time survival prediction with genomic feature masking, WSI dropout, and paired WSI-genomics contrastive alignment. Across four external evaluations in colon, renal, lung, and glioblastoma cohorts, MIST improves external C-index over standard fusion baselines in the primary comparisons. These results support genomic-guided histology attention as a compact and effective strategy for multimodal oncology outcome prediction. Our code is available at https://github.com/samiyavuuz/MIST .
Abstract:Multimodal survival models can combine complementary prognostic information from whole-slide images and genomic profiles, but effective fusion remains challenging amid external cohort shift and computational complexity. To address these challenges, we propose MIST, multimodal survival prediction with genomic-guided histology attention. MIST represents genomic features as tokens and allows them to query compact foundation-model-derived histology context tokens before survival prediction. This design enriches molecular information with histology context rather than merging separately encoded modalities only at the final stage. Training combines discrete-time survival prediction with genomic feature masking, WSI dropout, and paired WSI-genomics contrastive alignment. Across four external evaluations in colon, renal, lung, and glioblastoma cohorts, MIST improves external C-index over standard fusion baselines in the primary comparisons. These results support genomic-guided histology attention as a compact and effective strategy for multimodal oncology outcome prediction. Our code is available at this https URL .
Accepted at the COMPAYL 2026 Workshop on Computational Pathology and Multimodal Data at MICCAI 2026. 11 pages, 2 figures, 4 tables
Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2609.21811 [cs.AI]
(or arXiv:2609.21811v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.21811 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment
arXiv · Aug 6, 2026
Multi-Modal Tumor Survival Prediction via Graph-Guided Mixture of Experts
arXiv · Sep 15, 2026
CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction
arXiv · Aug 18, 2026
Spatial proteomics guided by H&E-based AI reveals recurrence-risk niches in triple-negative breast cancer
arXiv · Aug 5, 2026