Gliomas, particularly grade IV glioblastoma multiforme (GBM), represent the most common malignancy of the central nervous system and are associated with a dire prognosis, evidenced by a median survival time of less than 2 years [1]. The methylation status of the MGMT promoter, which is intricately linked to the levels of MGMT expression and consequently influences the tumor’s resistance to alkylating chemotherapy, has emerged as a pivotal diagnostic and prognostic indicator for GBM [2]. In standard clinical settings, the assessment of MGMT promoter methylation typically involves quantitative methylation-specific PCR or sequencing of tumor specimens obtained through surgical resection or biopsy. However, for patients for whom surgery is not an option or for those who have only undergone ablative treatments, the development of a non-invasive, imaging-based predictive methodology for assessing MGMT promoter methylation status holds significant clinical promise. This need is underscored by the lack of classical radiological indicators for MGMT status, a contrast to other glioma markers like isocitrate dehydrogenase (IDH) mutations. Thus, the creation of a prediction model for MGMT status, utilizing computer-automated radiomics features derived from magnetic resonance imaging scans, presents substantial challenges but also offers expanded clinical applicability [3].