Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction

arXiv:2401.01646v2 Announce Type: replace
Abstract: Multimodal learning significantly benefits cancer survival prediction, especially the integration of pathological images and genomic data. Despite advantages of multimodal learning for cancer survival prediction, massive redundancy in multimodal data prevents it from extracting discriminative and compact information: (1) An extensive amount of intra-modal task-unrelated information blurs discriminability, especially for gigapixel whole slide images (WSIs) with many patches in pathology and thousands of pathways in genomic data, leading to an ``intra-modal redundancy" issue. (2) Duplicated …

abstract advantages arxiv benefits cancer cs.cv data genomic genomic data images information integration massive modal multimodal multimodal data multimodal learning prediction redundancy survival type