Radiomics Profiling Identifies the Incremental Value of MRI Features beyond Key Molecular Biomarkers for the Risk Stratification of High-Grade Gliomas.
Objective: To identify the incremental value of magnetic resonance imaging (MRI) features beyond key molecular biomarkers for the risk stratification of high-grade gliomas (HGGs).
Methods: A total of 241 patients with preoperative magnetic resonance (MR) images and clinical and genetic data were retrospectively collected from our institution and The Cancer Genome Atlas/The Cancer Imaging Archive (TCGA/TCIA) dataset. Radiomic features (n = 1702) were extracted from both postcontrast T1-weighted (CE-T1) and T2-weighted fluid attenuation inversion recovery (T2FLAIR) MR images. The least absolute shrinkage and selection operator (LASSO) method was used to select effective features. A multivariate Cox proportional risk regression model was established to explore the prognostic value of clinical features, molecular biomarkers, and radiomic features. Kaplan-Meier survival analysis and the log-rank test were used to evaluate the prognostic model, and a stratified analysis was conducted to demonstrate the incremental value of the radiomics signature. A nomogram was developed to predict the 1-year, 2-year, and 3-year overall survival (OS) probabilities of the patients with HGGs.
Results: The radiomics signature provided significant prognostic value for the risk stratification of patients with HGGs. The combined model integrating the radiomics signature with clinical data (age) and O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status had the best prognostic value, with C-index values of 0.752 and 0.792 in the training set and external validation set, respectively. Stratified Kaplan-Meier survival analysis showed that the radiomics signature could identify the risk subgroups in different clinical and molecular subgroups.
Conclusion: This radiomics signature can be used for the risk stratification of patients with HGGs and has incremental value beyond key molecular biomarkers, providing a preoperative basis for individualized diagnosis and treatment decision-making.