Integrated Radiomics Model Combining Diffusion Kurtosis Imaging and Dynamic Contrast-Enhanced MRI for Predicting TERT...

Area of Science:

• Neuroimaging
• Oncology
• Radiomics
• Molecular Diagnostics

Background:

• Gliomas are primary brain tumors with varying molecular subtypes.
• Telomerase reverse transcriptase (TERT) promoter mutations are common in gliomas and impact prognosis.
• Accurate preoperative prediction of TERT mutation status is crucial for treatment planning.

Purpose of the Study:

• To evaluate a radiomics model integrating diffusion kurtosis imaging (DKI) and dynamic contrast-enhanced MRI (DCE-MRI) for predicting TERT promoter mutation status in gliomas.
• To compare the performance of combined DKI and DCE-MRI radiomics with single-modality models.

Main Methods:

• Retrospective analysis of 126 glioma patients with preoperative multiparametric MRI (DKI and DCE-MRI).
• Radiomics features extracted from DKI and DCE-MRI parameter maps.
• Least absolute shrinkage and selection operator (LASSO) regression for feature selection, followed by logistic regression for model construction and ROC analysis for performance evaluation.

Main Results:

• The combined DKI and DCE-MRI radiomics model achieved an area under the curve (AUC) of 0.961 in the training cohort and 0.943 in the validation cohort.
• The combined model demonstrated significantly superior performance compared to DKI-only or DCE-MRI-only models (p < 0.05).
• Validation cohort performance: 88.9% sensitivity, 95.0% specificity, and 92.1% accuracy; decision curve analysis showed significant clinical utility.

Conclusions:

• An integrated multiparametric radiomics model combining DKI and DCE-MRI enables accurate noninvasive preoperative prediction of TERT promoter mutation status in gliomas.
• This combined approach offers superior predictive performance and clinical utility over single-modality imaging.
• The model provides valuable imaging biomarkers for molecular stratification and personalized treatment planning in glioma patients.