Multiparametric MRI radiomics model for preoperative prediction of IDH1 R132H immunopositivity status in adult diffuse Glioma

Gliomas are the most common primary brain tumors, and isocitrate dehydrogenase (IDH) mutation status is a critical molecular marker influencing prognosis and treatment planning. This study aimed to evaluate the value of a multiparametric magnetic resonance imaging (MRI) radiomics model in predicting IDH1 R132H immunopositivity status in patients with gliomas. A retrospective analysis was conducted on 94 adult glioma patients at Viet Duc University Hospital from June 2024 to January 2026. All patients underwent preoperative MRI including conventional sequences, diffusion-weighted imaging (DWI), and dynamic susceptibility contrast perfusion imaging (DSC-MRI). Radiomics features were extracted from apparent diffusion coefficient (ADC) and relative cerebral blood volume (rCBV) maps within the tumor region, followed by correlation filtering and LASSO (Least Absolute Shrinkage and Selection Operator)-based feature selection, retaining 5 ADC and 10 rCBV features for logistic regression model construction. The ADC-based model achieved an area under the curve (AUC) of 0.875, the rCBV-based model reached 0.943, and the combined model achieved the highest numerical AUC (0.955), with an accuracy of 89.5%, sensitivity of 87.5%, and specificity of 90.9%, although the differences between models were not statistically significant. These findings suggest that multiparametric MRI radiomics demonstrates promising discriminatory performance for preoperative prediction of IDH1 R132H immunopositivity status in glioma patients, although these estimates derive from a single-center cohort with a small held-out test set and therefore require external validation in larger, prospective cohorts.