Skip to main content

ORIGINAL RESEARCH article

Front. Neurol.
Sec. Neuro-Oncology and Neurosurgical Oncology
Volume 16 - 2025 | doi: 10.3389/fneur.2025.1493666
This article is part of the Research Topic Artificial Intelligence and Omics Sciences Applied to Brain and CNS Tumors: New Insights and Perspectives View all articles

Radiomics prediction of MGMT promoter methylation in adult diffuse gliomas: a combination of structural MRI, DCE and DTI

Provisionally accepted
Yuying Liu Yuying Liu 1Zhengyang Zhu Zhengyang Zhu 2Jianan Zhou Jianan Zhou 2Han Wang Han Wang 2Huiquan Yang Huiquan Yang 2Jinfeng Yin Jinfeng Yin 3Yitong Wang Yitong Wang 4Xin Li Xin Li 2Futao Chen Futao Chen 2Qian Li Qian Li 2Zhuoru Jiang Zhuoru Jiang 2Xi Wu Xi Wu 2Danni Ge Danni Ge 2Yi Zhang Yi Zhang 2Xin Zhang Xin Zhang 2*Bing Zhang Bing Zhang 2
  • 1 Nanjing University, Nanjing, China
  • 2 Nanjing Drum Tower Hospital, Nanjing, Jiangsu Province, China
  • 3 Shandong Second Medical University, Weifang, Shandong Province, China
  • 4 Shandong First Medical University, Tai'an, Shandong, China

The final, formatted version of the article will be published soon.

    Purpose: To assess the predictive value of radiomics features extracted from Structural MRI, dynamic contrast enhanced (DCE), and diffusion tensor imaging (DTI) in detecting O6methylguanine-DNA methyltransferase (MGMT) promoter methylation in patients with diffuse gliomas.Retrospective MRI data of 110 patients were enrolled in this study. The training dataset included 88 patients (mean age 52.84±14.71, 47 females). The test dataset included 22 patients (mean age 50.64±12.58, 12 females). A total of 2782 radiomic features were extracted from Structural MRI, DCE and DTI within two region of interests (ROIs). Feature section was conducted using Pearson correlation and least absolute shrinkage and selection operator. Principal component analysis was utilized for dimensionality reduction. Support vector machine was employed for model construction.Two radiologists with 1 year and 5 years of experience evaluated the MGMT status in the test dataset as a comparison with the models. The chi-square test and independent samples t-test were used for assessing the statistical differences in patients' clinical characteristics.: On the training dataset, the model Structural MRI + DCE achieved the highest AUC of 0.906. On the test dataset, the model Structural MRI + DCE + DTI achieved the highest AUC of 0.868, outperforming two radiologists. Conclusion: The radiomics models have obtained promising performance in predicting MGMT promoter methylation status. Adding DCE and DTI features can provide extra information to structural MRI in detecting MGMT promoter methylation.

    Keywords: MGMT, Glioma, Radiomics, DCE, DTI

    Received: 09 Sep 2024; Accepted: 17 Jan 2025.

    Copyright: © 2025 Liu, Zhu, Zhou, Wang, Yang, Yin, Wang, Li, Chen, Li, Jiang, Wu, Ge, Zhang, Zhang and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Xin Zhang, Nanjing Drum Tower Hospital, Nanjing, 210008, Jiangsu Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.