MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma
Objective To explore the potential value of expert-identified CT and MRI imaging features in predicting the MGMT promoter methylation status in glioma. Methods A retrospective analysis was conducted in 188 patients in The First Medical Center of Chinese PLA General Hospital from January 2019 to Dec...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tianjin Huanhu Hospital
2025-07-01
|
| Series: | Chinese Journal of Contemporary Neurology and Neurosurgery |
| Subjects: | |
| Online Access: | http://www.cjcnn.org/index.php/cjcnn/article/view/3061 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850043868776497152 |
|---|---|
| author | ZHANG Zhi-zhong YOU Na LIU Ming-hang LI Ze SUN Guo-chen ZHAO Kai |
| author_facet | ZHANG Zhi-zhong YOU Na LIU Ming-hang LI Ze SUN Guo-chen ZHAO Kai |
| author_sort | ZHANG Zhi-zhong |
| collection | DOAJ |
| description | Objective To explore the potential value of expert-identified CT and MRI imaging features in predicting the MGMT promoter methylation status in glioma. Methods A retrospective analysis was conducted in 188 patients in The First Medical Center of Chinese PLA General Hospital from January 2019 to December 2020 with pathologically confirmed glioma. Imaging features were extracted, including calcification, clear lesion margins, peritumoral edema, T2WI/T2-FLAIR mismatch, cortical involvement, subventricular zone involvement, insular involvement, homogeneous signal on T2WI, and enhanced lesions. Pyrosequencing was used to detect the MGMT promoter methylation status. Univariate and multivariate Logistic regression analyses were used to find the imaging feature factors that affect the MGMT promoter methylation status. Then, by plotting the receiver operating characteristic (ROC) curve, verify the predictive efficacy of the imaging features. For the prediction task, further train and test 4 machine learning (ML) models, namely Logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting (GB). Results Logistic regression analysis showed that homogeneous signal on T2WI (OR = 2.843, 95%CI: 1.055-7.658; P = 0.039) and enhanced lesions (OR = 0.146, 95%CI: 0.069-0.308; P = 0.000) were imaging feature factors affecting the MGMT promoter methylation status. The comprehensive parameters combining both had higher prediction ability compared with homogeneous signal on T2WI (Z = 3.961, P = 0.000) and enhanced lesions (Z = 2.233, P = 0.026). The prediction accuracies rates of LR, SVM, RF and GB models were 0.84, 0.76, 0.68 and 0.76, respectively. However, there were no statistically significant differences in prediction efficacy when comparing the models pairwise (P > 0.05, for all). Conclusions Imaging features based on preoperative CT and MRI show promise for non-invasive prediction of MGMT promoter methylation status in glioma. |
| format | Article |
| id | doaj-art-df98a2d315714e8f9a3e403821faa464 |
| institution | DOAJ |
| issn | 1672-6731 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Tianjin Huanhu Hospital |
| record_format | Article |
| series | Chinese Journal of Contemporary Neurology and Neurosurgery |
| spelling | doaj-art-df98a2d315714e8f9a3e403821faa4642025-08-20T02:55:06ZengTianjin Huanhu HospitalChinese Journal of Contemporary Neurology and Neurosurgery1672-67312025-07-0125759560110.3969/j.issn.1672⁃6731.2025.07.005MRI feature-based discrimination model for prediction of MGMT promoter methylation status in gliomaZHANG Zhi-zhong0YOU Na1LIU Ming-hang2LI Ze3SUN Guo-chen4ZHAO Kai5Department of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaDepartment of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaDepartment of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaDepartment of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaDepartment of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaDepartment of Neurosurgery, The First Medical Center of Chinese PLA General Hospital, Beijing 100853, ChinaObjective To explore the potential value of expert-identified CT and MRI imaging features in predicting the MGMT promoter methylation status in glioma. Methods A retrospective analysis was conducted in 188 patients in The First Medical Center of Chinese PLA General Hospital from January 2019 to December 2020 with pathologically confirmed glioma. Imaging features were extracted, including calcification, clear lesion margins, peritumoral edema, T2WI/T2-FLAIR mismatch, cortical involvement, subventricular zone involvement, insular involvement, homogeneous signal on T2WI, and enhanced lesions. Pyrosequencing was used to detect the MGMT promoter methylation status. Univariate and multivariate Logistic regression analyses were used to find the imaging feature factors that affect the MGMT promoter methylation status. Then, by plotting the receiver operating characteristic (ROC) curve, verify the predictive efficacy of the imaging features. For the prediction task, further train and test 4 machine learning (ML) models, namely Logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting (GB). Results Logistic regression analysis showed that homogeneous signal on T2WI (OR = 2.843, 95%CI: 1.055-7.658; P = 0.039) and enhanced lesions (OR = 0.146, 95%CI: 0.069-0.308; P = 0.000) were imaging feature factors affecting the MGMT promoter methylation status. The comprehensive parameters combining both had higher prediction ability compared with homogeneous signal on T2WI (Z = 3.961, P = 0.000) and enhanced lesions (Z = 2.233, P = 0.026). The prediction accuracies rates of LR, SVM, RF and GB models were 0.84, 0.76, 0.68 and 0.76, respectively. However, there were no statistically significant differences in prediction efficacy when comparing the models pairwise (P > 0.05, for all). Conclusions Imaging features based on preoperative CT and MRI show promise for non-invasive prediction of MGMT promoter methylation status in glioma.http://www.cjcnn.org/index.php/cjcnn/article/view/3061gliomamagnetic resonance imagingo(6)-methylguanine-dna methyltransferaselogistic modelsmachine learning |
| spellingShingle | ZHANG Zhi-zhong YOU Na LIU Ming-hang LI Ze SUN Guo-chen ZHAO Kai MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma Chinese Journal of Contemporary Neurology and Neurosurgery glioma magnetic resonance imaging o(6)-methylguanine-dna methyltransferase logistic models machine learning |
| title | MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma |
| title_full | MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma |
| title_fullStr | MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma |
| title_full_unstemmed | MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma |
| title_short | MRI feature-based discrimination model for prediction of MGMT promoter methylation status in glioma |
| title_sort | mri feature based discrimination model for prediction of mgmt promoter methylation status in glioma |
| topic | glioma magnetic resonance imaging o(6)-methylguanine-dna methyltransferase logistic models machine learning |
| url | http://www.cjcnn.org/index.php/cjcnn/article/view/3061 |
| work_keys_str_mv | AT zhangzhizhong mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma AT youna mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma AT liuminghang mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma AT lize mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma AT sunguochen mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma AT zhaokai mrifeaturebaseddiscriminationmodelforpredictionofmgmtpromotermethylationstatusinglioma |