Radiomics Features Predict CIC Mutation Status in Lower Grade Glioma

Area of Science:

• Neuro-oncology
• Radiomics
• Genomics

Background:

• MRI and genomic markers are crucial for glioma management.
• Radiomics and radiogenomics enable quantitative tumor assessment for predicting molecular subtypes and disease progression.

Purpose of the Study:

• To investigate the effect of Drosophila gene capicua (CIC) mutation biomarker and radiomics features on predicting CIC mutation status in lower-grade gliomas (LGG).

Main Methods:

• Utilized genomic data from The Cancer Genome Atlas (TCGA) (n = 509) and MR images from TCIA (n = 120) for LGG patients.
• Extracted radiomics features from T1, T2, T2 Flair, and T1 contrast-enhanced (CE) MR images after tumor segmentation.
• Employed Lasso feature reduction and logistic regression to predict CIC mutation status.

Main Results:

• CIC mutation was rare in Astrocytoma but frequent in Oligodendroglioma.
• CIC mutation presence correlated with better glioma patient survival (p < 1e-4, HR: 0.2445), even with IDH mutation and 1p/19q co-deletion.
• An eleven-feature model achieved 94.2% accuracy for glioma prediction, and a six-feature model achieved 92.3% accuracy for oligodendroglioma prediction.

Conclusions:

• CIC is a potential prognostic factor in glioma, associated with improved survival.
• MRI radiomic features can predict CIC mutation status and indicate less malignant glioma characteristics.
• This approach can aid clinical judgment in glioma management.