Clinical-Radiomic Integration for Postoperative Glioma Recurrence and Survival Prediction

Postoperative magnetic resonance imaging (MRI) captures anatomical and tissue characteristics relevant to glioma prognosis. We evaluated the contribution of compartment-specific imaging features to clinical and molecular prediction using MU-Glioma-Post. Of 187 patients with usable radiomics, 111 were eligible for 180-day recurrence/progression prediction and 114 were eligible for 365-day mortality prediction after the first available postoperative MRI (TP1). Clinical-only, radiomics-only, and combined elastic-net logistic models were assessed using nested cross-validation and a locked internal holdout. For recurrence, the combined model achieved development out-of-fold (OOF) and holdout areas under the receiver operating characteristic curve (AUROCs) of 0.742 and 0.786 (95% confidence interval, 0.562–0.959), respectively. Morphology was the highest-ranking imaging-only configuration (OOF AUROC, 0.724), and flatness of the surrounding non-enhancing FLAIR hyperintensity led the SHAP feature ranking. In exploratory repeated nested cross-validation, adding shape, volume, and region-presence features to clinical predictors increased mean recurrence AUROC from 0.743 to 0.794, compared with 0.747 for clinical predictors combined with full radiomics. Clinical predictors remained the main source of mortality discrimination, with mean AUROCs of 0.774 for clinical predictors, 0.777 with morphology, and 0.768 with full radiomics. These findings identify postoperative geometry as a promising source of recurrence-related information and support focused integration of morphological features with clinical predictors.