MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network

Mingzhe Hu; Kailin Yang; Jing Wang; Richard L J Qiu; Justin Roper; Shannon Kahn; Hui-Kuo Shu; Xiaofeng Yang

doi:10.1117/1.JMI.11.1.014503

MGMT promoter methylation prediction based on multiparametric MRI via vision graph neural network

J Med Imaging (Bellingham). 2024 Jan;11(1):014503. doi: 10.1117/1.JMI.11.1.014503. Epub 2024 Feb 16.

Authors

Mingzhe Hu^{1

2}, Kailin Yang³, Jing Wang¹, Richard L J Qiu¹, Justin Roper¹, Shannon Kahn¹, Hui-Kuo Shu¹, Xiaofeng Yang^{1

2

4}

Affiliations

¹ Emory University, Department of Radiation Oncology and Winship Cancer Institute, Atlanta, Georgia, United States.
² Emory University, Department of Computer Science and Informatics, Atlanta, Georgia, United States.
³ Cleveland Clinic, Taussig Cancer Center, Department of Radiation Oncology, Cleveland, Ohio, United States.
⁴ Georgia Institute of Technology and Emory University, Department of Biomedical Engineering, Atlanta, Georgia, United States.

PMID: 38370421
PMCID: PMC10869845 (available on 2025-02-16)
DOI: 10.1117/1.JMI.11.1.014503

Abstract

Purpose: Glioblastoma (GBM) is aggressive and malignant. The methylation status of the $O^{6}$ -methylguanine-DNA methyltransferase (MGMT) promoter in GBM tissue is considered an important biomarker for developing the most effective treatment plan. Although the standard method for assessing the MGMT promoter methylation status is via bisulfite modification and deoxyribonucleic acid (DNA) sequencing of biopsy or surgical specimens, a secondary automated method based on medical imaging may improve the efficiency and accuracy of those tests.

Approach: We propose a deep vision graph neural network (ViG) using multiparametric magnetic resonance imaging (MRI) to predict the MGMT promoter methylation status noninvasively. Our model was compared to the RSNA radiogenomic classification winners. The dataset includes 583 usable patient cases. Combinations of MRI sequences were compared. Our multi-sequence fusion strategy was compared with those using single MR sequences.

Results: Our best model [Fluid Attenuated Inversion Recovery (FLAIR), T1-weighted pre-contrast (T1w), T2-weighted (T2)] outperformed the winning models with a test area under the curve (AUC) of 0.628, an accuracy of 0.632, a precision of 0.646, a recall of 0.677, a specificity of 0.581, and an F1 score of 0.661. Compared to the winning models with single MR sequences, our ViG utilizing fused-MRI showed a significant improvement statistically in AUC scores, which are FLAIR ( $p = 0.042$ ), T1w ( $p = 0.017$ ), T1wCE ( $p = 0.001$ ), and T2 ( $p = 0.018$ ).

Conclusions: Our model is superior to challenge champions. A graph representation of the medical images enabled good handling of complexity and irregularity. Our work provides an automatic secondary check pipeline to ensure the correctness of MGMT methylation status prediction.

Keywords: O6-methylguanine-DNA methyltransferase promoter methylation; deep learning; glioblastoma; graph neural network; magnetic resonance imaging; prognostic biomarker.