<scp>Non‐invasive</scp> prediction of overall survival time for glioblastoma multiforme patients based on multimodal <scp>MRI</scp> radiomics

Glioblastoma multiforme (GBM) is the most common and deadly primary malignant brain tumor. As GBM tumor aggressive shows high biological heterogeneity, overall survival (OS) time extremely low even with treatment. If OS can be predicted before surgery, developing personalized treatment plans for patients will beneficial. Magnetic resonance imaging (MRI) a commonly used diagnostic tool tumors high-resolution sound effects. However, in clinical practice, doctors mainly rely on manually segmenting regions MRI predicting of patients, which time-consuming, subjective repetitive, limiting effectiveness diagnosis Therefore, it crucial to segment MRI, an accurate pre-operative prediction highly desired. In this study, we present multimodal radiomics-based automatic framework non-invasive patients. A modified 3D-UNet model built subregions patients; then, radiomic features are extracted combined input into Support Vector Regression (SVR) predict time. experiments, BraTS2020, BraTS2019 BraTS2018 datasets evaluate our framework. Our achieves competitive accuracy compared typical approaches.