Non-invasive differentiation of diffuse midline glioma and midline glioblastoma using DCE-MRI perfusion parameters and machine learning classification in pediatric and young adult patients.
Authors
Affiliations (6)
Affiliations (6)
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India. [email protected].
- Department of Radiology and Neurosurgery, Fortis Memorial Research Institute, Gurgaon, India.
- Department of Pathology, Agilus Diagnostics, Fortis Memorial Research Institute, Gurgaon, India.
- Department of Neurosurgery, Fortis Memorial Research Institute, Gurgaon, India.
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India. [email protected].
- Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India. [email protected].
Abstract
Diffuse midline glioma (DMG) and midline glioblastoma (mGBM) are aggressive WHO grade 4 tumors with comparable median survival of 12-18 months but require fundamentally different therapeutic approaches. DMG is molecularly defined by H3 K27-alteration, whereas mGBM lacks this alteration, however, non-invasive differentiation remains challenging due to overlapping conventional MRI features and the difficulty of obtaining tissue diagnosis from eloquent midline locations. This retrospective study included 62 patients with histologically confirmed midline gliomas (30 mGBM, 32 DMG) evaluated with 3T MRI. Quantitative DCE-MRI perfusion parameters (rCBV, rCBF, Slope-2, K<sup>trans</sup>, V<sub>p</sub>, V<sub>e</sub>) were computed and compared between the midline tumor types. Statistical analyses included Shapiro-Wilk test, t-test, and ROC curve analysis using perfusion parameters. Machine learning-based classification was also performed using four classifiers and 5-fold cross-validation, evaluating all possible feature combinations among the best features from the perfusion parameters. Among the statistical features extracted from each parametric map, the 95<sup>th</sup> percentile values showed the highest discriminative performance for differentiating mGBM from DMG, outperforming the mean, standard deviation, and other percentile measures. DMG exhibited significantly lower 95<sup>th</sup> percentile perfusion parameter values compared to mGBM (p < 0.05). Individual perfusion parameters, particularly rCBF, rCBV, V<sub>e</sub> showed discriminative performance achieving AUC values ranging from 70.62% to 75.31%, for differentiating mGBM vs. DMG. Machine learning classifiers used these features for evaluating 7 combinations. Three parameter combination (rCBV + rCBF + V<sub>e</sub>) using a random forest classifier achieved the highest cross-validation accuracy (76.67 ± 7.16%) with consistent sensitivity (80.00%) across all models. Quantitative DCE-MRI perfusion analysis provides significant diagnostic value for differentiating DMG from mGBM, offering a non-invasive alternative when tissue diagnosis is not obtained. Both individual parameters and optimized multi-parametric approaches demonstrate clinically useful performance for guiding treatment decisions.