Multiparametric MRI Radiomics and Machine Learning Framework for Predicting Treatment Response in Glioblastoma
Abstract
Distinguishing True Progression (TP) from Pseudo-Progression (PsP) after chemoradiotherapy remains a major diagnostic challenge in GBM, as both entities present near-identical appearances on conventional contrast-enhanced post-treatment MRI. This distinction carries substantial clinical weight, since TP and PsP demand divergent management yet cannot be reliably separated on routine imaging alone. We investigated whether radiomic features derived from a parsimonious, voxel-wise pharmacokinetic model of dynamic contrast-enhanced (DCE) MRI, combined with MGMT status, could discriminate between the two. The cohort comprised 82 adults with IDH-wildtype GBM who developed a new contrast-enhancing lesion within six months of chemoradiotherapy; classification (53 TP, 29 PsP) was established by histopathology where available (n=52) and modified RANO criteria otherwise (n=30). At every voxel, contrast-concentration time courses were fitted to five candidate pharmacokinetic models, and the best fit was retained by AIC minimisation, yielding parsimonious Ktrans, Ve, Vp, and taui maps adapting to local heterogeneity rather than a single fixed model across the tumour. Following segmentation, 1,073 radiomic descriptors were extracted and reduced via Mann-Whitney U filtering and Elastic Net, then used to train five classifiers across four feature configurations. A Random Forest classifier combining parsimonious DCE-MRI radiomics with MGMT status achieved the best discrimination (mean AUC 0.89, sensitivity 0.93, specificity 0.76, F1 0.90), outperforming features without MGMT (0.84), a T1-post-contrast baseline (0.72), and a single-model extended-Tofts analysis (0.68). Shape and textural descriptors of the Ktrans map, with tumour volume, were the strongest predictors, MGMT contributing a smaller, independent effect. Allowing the model to vary voxel-wise improves non-invasive discrimination.
Related
- Cascaded Dual-Targeting (WTW/TAT) Liposomes Delivery DOX for Precision Glioblastoma Treatment
- Combinatorial treatment with formononetin and magnolol induces synergistic cytotoxicity and suppresses migration in glioblastoma cells
- Predicting the clinical course of advanced systemic mastocytosis on treatment with avapritinib or midostaurin
- Resting-state functional connectivity of hippocampal subregions in predicting escitalopram treatment outcome in major depressive disorder
- GlycoMAC: A Multiscale Metabolic-Glycosylation Framework for Predicting Glycosylation Across Conditions in Mammalian Cell Cultures
BibTeX
@misc{patra2026multiparametric,
title = {{Multiparametric MRI Radiomics and Machine Learning Framework for Predicting Treatment Response in Glioblastoma}},
author = {Suchibrata Patra},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.05733},
eprint = {2608.05733},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.05733},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Multiparametric MRI Radiomics and Machine Learning Framework for Predicting Treatment Response in Glioblastoma
AU - Suchibrata Patra
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2608.05733
UR - https://arxiv.org/abs/2608.05733
AB - Distinguishing True Progression (TP) from Pseudo-Progression (PsP) after chemoradiotherapy remains a major diagnostic challenge in GBM, as both entities present near-identical appearances on conventional contrast-enhanced post-treatment MRI. This distinction carries substantial clinical weight, since TP and PsP demand divergent management yet cannot be reliably separated on routine imaging alone. We investigated whether radiomic features derived from a parsimonious, voxel-wise pharmacokinetic model of dynamic contrast-enhanced (DCE) MRI, combined with MGMT status, could discriminate between the two. The cohort comprised 82 adults with IDH-wildtype GBM who developed a new contrast-enhancing lesion within six months of chemoradiotherapy; classification (53 TP, 29 PsP) was established by histopathology where available (n=52) and modified RANO criteria otherwise (n=30). At every voxel, contrast-concentration time courses were fitted to five candidate pharmacokinetic models, and the best fit was retained by AIC minimisation, yielding parsimonious Ktrans, Ve, Vp, and taui maps adapting to local heterogeneity rather than a single fixed model across the tumour. Following segmentation, 1,073 radiomic descriptors were extracted and reduced via Mann-Whitney U filtering and Elastic Net, then used to train five classifiers across four feature configurations. A Random Forest classifier combining parsimonious DCE-MRI radiomics with MGMT status achieved the best discrimination (mean AUC 0.89, sensitivity 0.93, specificity 0.76, F1 0.90), outperforming features without MGMT (0.84), a T1-post-contrast baseline (0.72), and a single-model extended-Tofts analysis (0.68). Shape and textural descriptors of the Ktrans map, with tumour volume, were the strongest predictors, MGMT contributing a smaller, independent effect. Allowing the model to vary voxel-wise improves non-invasive discrimination.
ER -