Pathology-genomic fusion via biologically informed cross-modality graph learning for survival analysis

arXiv:2404.08023v1 Announce Type: cross
Abstract: The diagnosis and prognosis of cancer are typically based on multi-modal clinical data, including histology images and genomic data, due to the complex pathogenesis and high heterogeneity. Despite the advancements in digital pathology and high-throughput genome sequencing, establishing effective multi-modal fusion models for survival prediction and revealing the potential association between histopathology and transcriptomics remains challenging. In this paper, we propose Pathology-Genome Heterogeneous Graph (PGHG) that integrates whole slide images (WSI) and bulk RNA-Seq expression …

abstract analysis arxiv cancer clinical cs.lg data diagnosis digital digital pathology fusion genome genomic genomic data graph graph learning images modal multi-modal pathology q-bio.qm sequencing survival type via