Diffusion-Weighted MRI Radiomics Model for Differentiating High-Grade Gliomas in Non-Enhancing (Low-Grade Appearance) Gliomas

Motivation: Approximately 8% to 18% of non-enhancing(non-CE) gliomas ultimately diagnosed as glioblastoma lack contrast enhancement and exhibit a 'low-grade appearance' on imaging. This may lead to misdiagnosis, treatment delays, and adverse patient outcomes. Goal(s): Apply radiomics to build a preoperative predictive model and assess its value in differentiating non-CE high-grade gliomas preoperatively. Approach: The T2WI, T1CE and ADC sequences of patients with pathologically confirmed glioma were retrospectively analyzed. Diagnostic performance was evaluated using the AUC. Results: The multi-parametric sequence (T2WI + T1CE + ADC) achieved the highest AUC, with an AUC of 0.892,in the training set and 0.805 in the validation set. Impact: The radiomics model based on diffusion MRI can non-invasively differentiate between high-grade and low-grade gliomas in non-CE adult diffuse gliomas,providing valuable support for decision-making in clinical surgical strategies and prognostic management.