Explainable Deep Radiogenomic Molecular Imaging for MGMT Methylation Prediction in Glioblastoma

TL;DR

This work tackles noninvasive MGMT promoter methylation prediction in glioblastoma by integrating multi-parametric MRI radiomics with deep learning in a radiogenomic framework. It introduces ResUNetVSA, a 3D segmentation backbone with variable-scale attention and boundary-aware regularization, coupled with a hybrid radiomics–deep representation for MGMT classification. External validation on UCSD-PTGBM and cross-validation on BraTS 2021 show robust performance (segmentation macro Dice ≈ 0.912; MGMT ROC–AUC ≈ 0.82 on external data), while Grad-CAM and SHAP provide explainability for clinical interpretability. The approach demonstrates strong cross-site generalization, preserves biologically meaningful imaging phenotypes through radiomic features, and highlights a practical path toward noninvasive, explainable molecular biomarkers in precision oncology.

Abstract

Glioblastoma (GBM) is a highly aggressive primary brain tumor with limited therapeutic options and poor prognosis. The methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) gene promoter is a critical molecular biomarker that influences patient response to temozolomide chemotherapy. Traditional methods for determining MGMT status rely on invasive biopsies and are limited by intratumoral heterogeneity and procedural risks. This study presents a radiogenomic molecular imaging analysis framework for the non-invasive prediction of MGMT promoter methylation using multi-parametric magnetic resonance imaging (mpMRI). Our approach integrates radiomics, deep learning, and explainable artificial intelligence (XAI) to analyze MRI-derived imaging phenotypes and correlate them with molecular labels. Radiomic features are extracted from FLAIR, T1-weighted, T1-contrast-enhanced, and T2-weighted MRI sequences, while a 3D convolutional neural network learns deep representations from the same modalities. These complementary features are fused using both early fusion and attention-based strategies and classified to predict MGMT methylation status. To enhance clinical interpretability, we apply XAI methods such as Grad-CAM and SHAP to visualize and explain model decisions. The proposed framework is trained on the RSNA-MICCAI Radiogenomic Classification dataset and externally validated on the BraTS 2021 dataset. This work advances the field of molecular imaging by demonstrating the potential of AI-driven radiogenomics for precision oncology, supporting non-invasive, accurate, and interpretable prediction of clinically actionable molecular biomarkers in GBM.

Figures (11)

• Figure 1: Overall pipeline. Left: MRI feature extraction (preprocessing, segmentation, radiomics, deep features, and feature fusion). Right: training, prediction, and interpretability.
• Figure 2: Overview of the preprocessing pipeline. The pipeline includes bias-field correction, brain extraction, ROI specification and cropping, intensity standardization, grid harmonization, and label canonicalization, resulting in standardized, size-safe volumes and canonical tumor labels.
• Figure 3: Representative axial slices for one subject. Top: raw FLAIR/T1/T1CE/T2. Bottom: normalized images with tumor overlay; all modalities use the same slice index.
• Figure 4: Segmentation pipeline. The ResUNetVSA backbone integrates residual convolutional blocks, variable-scale attention (VSA), channel and spatial gating, and skip connections. Training employs a hybrid loss combining cross-entropy, soft Dice over tumor subregions, and a cosine-ramped boundary regularizer to improve boundary delineation.
• Figure 5: Overview of the proposed hybrid pipeline for MGMT promoter methylation prediction. Multi-parametric MRIs and segmentation masks are preprocessed into 8-channel crops, processed through radiomics and deep learning feature extraction branches, fused into a joint representation, and classified with a gradient boosted machine (GBM).