Deep learning-based prediction of TERT mutation status from MRI for glioma molecular subtyping

Key Points

• The RegNet model predicts TERT promoter mutation status from routine MRI scans, offering a non-invasive diagnostic alternative.
• Prediction accuracy for TERT mutations was validated, suggesting a robust application in glioma subtyping and management.
• Analysis employs deep learning techniques to process MRI images, enhancing diagnostic capabilities without tissue sampling.
• Further validation with multi-center data is necessary to confirm findings and improve clinical integration.