arXiv Computer Vision
HGASurv: Hierarchical Granularity-Aware Multimodal Integration for Survival Prediction
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 18
ChronoSurv: A Clinical Pathway-Guided Graph Framework for Multimodal Survival Analysis
arXiv:2606. 19140v1 Announce Type: new Abstract: Accurate survival prediction is essential for personalized treatment planning in head and neck cancer, yet remains challenging due to the heterogeneous and high-dimensional nature of multimodal clinical data.
arXiv Computer Vision
Oct 7
Anchor-driven Multi-modal Multi-scale Expert Selection for Survival Prediction
arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival predi...
arXiv Machine Learning
Jun 3
Graph Mamba Survival Analysis Based on Topology-Aware ordering
arXiv:2606. 02602v1 Announce Type: new Abstract: In computational pathology, Whole Slide Images (WSIs) survival analysis is crucial for patient prognosis assessment, but it faces multiple technical challenges.
arXiv Computer Vision
Sep 1
Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Prediction
arXiv:2510.06113v2 Announce Type: replace Abstract: Survival analysis plays a vital role in making clinical decisions. However, the models currently in use are often difficult to interpret, which red...
arXiv AI
Jul 21
AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis
arXiv:2607. 16260v1 Announce Type: cross Abstract: Multimodal survival analysis utilizing whole slide images (WSIs) and genomic profiles is fundamental for cancer prognosis.
arXiv AI
Sep 21
MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention
MIST is a multimodal survival prediction framework that fuses whole-slide images and genomic profiles by representing genomic features as tokens that query histology context tokens derived from a foundation model. The architecture enriches molecular information with histology context before survival prediction, avoiding late-stage merging of separately encoded modalities. Training incorporates discrete-time survival prediction, genomic feature masking, WSI dropout, and contrastive alignment, and demonstrates improved external C-index across colon, renal, lung, and glioblastoma cohorts compared to standard fusion baselines.