Learning MRI-based classification models for MGMT methylation status prediction in glioblastoma

Abstract

Background and objective: The O⁶-methylguanine-DNA-methyltransferase (MGMT) promoter methylation has been shown to be associated with improved outcomes in patients with glioblastoma (GBM) and may be a predictive marker of sensitivity to chemotherapy. However, determination of the MGMT promoter methylation status requires tissue obtained via surgical resection or biopsy. The aim of this study was to assess the ability of quantitative and qualitative imaging variables in predicting MGMT methylation status noninvasively.

Methods: A retrospective analysis of MR images from GBM patients was conducted. Multivariate prediction models were obtained by machine-learning methods and tested on data from The Cancer Genome Atlas (TCGA) database.

Results: The status of MGMT promoter methylation was predicted with an accuracy of up to 73.6%. Experimental analysis showed that the edema/necrosis volume ratio, tumor/necrosis volume ratio, edema volume, and tumor location and enhancement characteristics were the most significant variables in respect to the status of MGMT promoter methylation in GBM.

Conclusions: The obtained results provide further evidence of an association between standard preoperative MRI variables and MGMT methylation status in GBM.

Keywords: Feature extraction; Glioblastoma; MGMT promoter methylation; Multivariate analysis; Prediction model.