Biological mechanisms underlying prognostic radiomic models based on dynamic susceptibility contrast perfusion-weighted imaging in gliomas

Motivation: The biological mechanisms underlying DSC-PWI-based prognostic radiomic models remain poorly understood. Goal(s): To uncover the biological basis of prognostic radiomic models in glioma patients using paired DSC-PWI and RNA-seq data. Approach: A radiomic risk signature (RRS) for overall survival prediction was developed using preoperative DSC-PWI. Gene Set Enrichment Analysis and Weighted Gene Co-expression Network Analysis were employed to identify biological pathways associated with the RRS and individual prognostic radiomic features, utilizing both DSC-PWI and RNA-seq data. Results: The RRS independently predicted patient survival. The biological basis of prognostic radiomic models involve key pathways related to angiogenesis-hypoxia, immunity and proliferation. Impact: Our work presents an accurate and biologically meaningful tool for survival prediction in gliomas, facilitating personalized clinical decision-making through a non-invasive approach.