Novel Local Radiomic Bayesian Classifiers for Non-Invasive Prediction of MGMT Methylation Status in Glioblastoma

TL;DR

This paper introduces novel Bayesian classifiers that utilize local radiomic features from MRI scans to non-invasively predict MGMT methylation status in glioblastoma, potentially replacing invasive biopsy procedures.

Contribution

The work presents new local radiomic Bayesian classifiers that improve MGMT methylation prediction accuracy from MRI data compared to global feature models.

Findings

Bayesian classifiers enhance prediction performance with local radiomic features.

Local radiomic analysis outperforms global feature approaches.

Proposed method offers a non-invasive alternative for MGMT status determination.

Abstract

Glioblastoma, an aggressive brain cancer, is amongst the most lethal of all cancers. Expression of the O6-methylguanine-DNA-methyltransferase (MGMT) gene in glioblastoma tumor tissue is of clinical importance as it has a significant effect on the efficacy of Temozolomide, the primary chemotherapy treatment administered to glioblastoma patients. Currently, MGMT methylation is determined through an invasive brain biopsy and subsequent genetic analysis of the extracted tumor tissue. In this work, we present novel Bayesian classifiers that make probabilistic predictions of MGMT methylation status based on radiomic features extracted from FLAIR-sequence magnetic resonance imagery (MRIs). We implement local radiomic techniques to produce radiomic activation maps and analyze MRIs for the MGMT biomarker based on statistical features of raw voxel-intensities. We demonstrate the ability for simple Bayesian classifiers to provide a boost in predictive performance when modelling local radiomic data rather than global features. The presented techniques provide a non-invasive MRI-based approach to determining MGMT methylation status in glioblastoma patients.