Answers are grounded in this paper and cite their sources.
This machine learning approach predicts mgmt methylation status using MRI features, highlighting accuracy and implications for GBM treatment.
Glioblastoma (GBM) is the most aggressive primary brain tumor in adults, marked by high recurrence rates and poor prognosis. The methylation status of the O-6-methylguanine-DNA methyltransferase (MGMT) gene promoter plays a critical role in determining treatment response and patient survival. This work provides non-invasive machine learning (ML) solution for prediction of MGMT methylation status using features of magnetic resonance imaging (MRI) scans, aiming to support personalized therapeutic strategies. The method involves a three-step pipeline: First, extraction of image features from multi-modal MR. Second, Selection of the most important common features using light gradient boosting machine (LightGBM) algorithm and categorical gradient boosting (CatBoost). then, a voting ensemble of multiple ML models is trained on the selected features to classify MGMT methylation. The model was developed using Brain Tumor Segmentation (BraTS) 2021 dataset, which includes both segmentation masks and MGMT annotations. Its performance was evaluated using accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). The model achieved an accuracy of 92.86% and AUC of 96.84%, demonstrating strong alignment with clinical outcomes and surpassing conventional methods. These findings highlight the effectiveness of features extraction from multi-modal MRI analysis, and ML-based classification for biomarker prediction. The approach offers a promising step forward in precision medicine for GBM, enabling more accurate and individualized treatment planning.
No takes yet. Share an insight, caveat, or question.
Boulkhiout et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: