Distinction of True-Progression from Pseudo-progression in Glioblastomas using ML Model based on Quantitative mpMRI and Molecular Signatures

Glioblastoma patients (n=93) exhibiting enhancing lesions within 6 months after completion of standard therapy underwent anatomical imaging, diffusion and perfusion MRI. The median values of parameters (MD, FA, CL, CP, CS and rCBV) were computed from the enhancing regions. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status was available from 75 patients. Subsequently, these patients were classified as TP (n=55) or PsP (n=20). The data were randomly split into training and testing sets. The best model for differentiating TP from PsP was obtained using quadratic SVM classifier with a training accuracy of 90.9%, cross-validation accuracy of 85.5% and testing accuracy of 85%.