Glioblastoma (GBM) is well-known for its molecular and spatial heterogeneity, which poses a challenge for precision therapies and clinical trial stratification. Here, in a comprehensive radiogenomics study of 358 GBMs, we investigated the associations between the imaging and spatial characteristics of the tumors with their cancer gene mutation status, as well as with the cross-sectionally inferred likely order of mutational events. We show that cross-validated machine learning analysis of multi-parametric MRI scans results in distinctivein vivoimaging signatures of several mutations, which are relatively more distinctive in homogeneous tumors which harbor only one of these mutations. These imaging signatures offer mechanistic insights into how various mutations influence the phenotype of the tumor and its surrounding infiltrated brain tissue via neovascularization and vascular leakage, increased cell density, invasion and migration, and other characteristics captured by respective imaging features. Furthermore, we found that spatial location and tumor distribution vary, depending on the GBM’s molecular characteristics. Finally, distinct imaging and spatial characteristics were associated with cross-sectionally estimated evolutionary trajectories of the tumors. Collectively, our study establishes a panel ofin vivoand clinically accessible imaging-AI biomarkers of GBM that reflect their molecular composition and oncogenic drivers.
