Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model

Abstract Background Accurately distinguishing the different molecular subtypes of 2021 World Health Organization (WHO) grade 4 Central Nervous System (CNS) gliomas is highly relevant for prognostic stratification and personalized treatment. Objectives To develop and validate a machine learning (ML)...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenji Xu, Yangyang Li, Jie Zhang, Zhiyi Zhang, Pengxin Shen, Xiaochun Wang, Guoqiang Yang, Jiangfeng Du, Hui Zhang, Yan Tan
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Cancer
Subjects:
Online Access:https://doi.org/10.1186/s12885-025-14529-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343646630936576
author Wenji Xu
Yangyang Li
Jie Zhang
Zhiyi Zhang
Pengxin Shen
Xiaochun Wang
Guoqiang Yang
Jiangfeng Du
Hui Zhang
Yan Tan
author_facet Wenji Xu
Yangyang Li
Jie Zhang
Zhiyi Zhang
Pengxin Shen
Xiaochun Wang
Guoqiang Yang
Jiangfeng Du
Hui Zhang
Yan Tan
author_sort Wenji Xu
collection DOAJ
description Abstract Background Accurately distinguishing the different molecular subtypes of 2021 World Health Organization (WHO) grade 4 Central Nervous System (CNS) gliomas is highly relevant for prognostic stratification and personalized treatment. Objectives To develop and validate a machine learning (ML) model using multiparametric MRI for the preoperative differentiation of astrocytoma, CNS WHO grade 4, and glioblastoma (GBM), isocitrate dehydrogenase-wild-type (IDH-wt) (WHO 2021) (Task 1:grade 4 vs. GBM); and to stratify astrocytoma, CNS WHO grade 4, by distinguish astrocytoma, IDH-mutant (IDH-mut), CNS WHO grade 4 from astrocytoma, IDH-wild-type (IDH-wt), CNS WHO grade 4 (Task 2:IDH-mut grade 4 vs. IDH-wt grade 4). Additionally, to evaluate the model’s prognostic value. Methods We retrospectively analyzed 320 glioma patients from three hospitals (training/testing, 7:3 ratio) and 99 patients from ‌The Cancer Genome Atlas (TCGA) database for external validation‌. Radiomic features were extracted from tumor and edema on contrast-enhanced T1-weighted imaging (CE-T1WI) and T2 fluid-attenuated inversion recovery (T2-FLAIR). Extreme gradient boosting (XGBoost) was utilized for constructing the ML, clinical, and combined models. Model performance was evaluated with receiver operating characteristic (ROC) curves, decision curves, and calibration curves. Stability was evaluated using six additional classifiers. Kaplan-Meier (KM) survival analysis and the log-rank test assessed the model’s prognostic value. Results In Task 1 and Task 2, the combined model (AUC = 0.907, 0.852 and 0.830 for Task 1; AUC = 0.899, 0.895 and 0.792 for Task 2) and the optimal ML model (AUC = 0.902, 0.854 and 0.832 for Task 1; AUC = 0.904, 0.899 and 0.783 for Task 2) significantly outperformed the clinical model (AUC = 0.671, 0.656, and 0.543 for Task 1; AUC = 0.619, 0.605 and 0.400 for Task 2) in both the training, testing and validation sets. Survival analysis showed the combined model performed similarly to molecular subtype in both tasks (p = 0.964 and p = 0.746). Conclusion The multiparametric MRI ML model effectively distinguished astrocytoma, CNS WHO grade 4 from GBM, IDH-wt (WHO 2021) and differentiated astrocytoma, IDH-mut from astrocytoma, IDH-wt, CNS WHO grade 4. Additionally, the model provided reliable survival stratification for glioma patients across different molecular subtypes.
format Article
id doaj-art-7e422252d41d406592e8a8db7b3e9783
institution Kabale University
issn 1471-2407
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Cancer
spelling doaj-art-7e422252d41d406592e8a8db7b3e97832025-08-20T03:42:53ZengBMCBMC Cancer1471-24072025-07-0125111610.1186/s12885-025-14529-7Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning modelWenji Xu0Yangyang Li1Jie Zhang2Zhiyi Zhang3Pengxin Shen4Xiaochun Wang5Guoqiang Yang6Jiangfeng Du7Hui Zhang8Yan Tan9College of Medical Imaging, Shanxi Medical UniversityCollege of Medical Imaging, Shanxi Medical UniversityCollege of Medical Imaging, Shanxi Medical UniversityCollege of Medical Imaging, Shanxi Medical UniversityCollege of Medical Imaging, Shanxi Medical UniversityDepartment of Radiology, First Hospital of Shanxi Medical UniversityDepartment of Radiology, First Hospital of Shanxi Medical UniversityDepartment of Radiology, First Hospital of Shanxi Medical UniversityDepartment of Radiology, First Hospital of Shanxi Medical UniversityDepartment of Radiology, First Hospital of Shanxi Medical UniversityAbstract Background Accurately distinguishing the different molecular subtypes of 2021 World Health Organization (WHO) grade 4 Central Nervous System (CNS) gliomas is highly relevant for prognostic stratification and personalized treatment. Objectives To develop and validate a machine learning (ML) model using multiparametric MRI for the preoperative differentiation of astrocytoma, CNS WHO grade 4, and glioblastoma (GBM), isocitrate dehydrogenase-wild-type (IDH-wt) (WHO 2021) (Task 1:grade 4 vs. GBM); and to stratify astrocytoma, CNS WHO grade 4, by distinguish astrocytoma, IDH-mutant (IDH-mut), CNS WHO grade 4 from astrocytoma, IDH-wild-type (IDH-wt), CNS WHO grade 4 (Task 2:IDH-mut grade 4 vs. IDH-wt grade 4). Additionally, to evaluate the model’s prognostic value. Methods We retrospectively analyzed 320 glioma patients from three hospitals (training/testing, 7:3 ratio) and 99 patients from ‌The Cancer Genome Atlas (TCGA) database for external validation‌. Radiomic features were extracted from tumor and edema on contrast-enhanced T1-weighted imaging (CE-T1WI) and T2 fluid-attenuated inversion recovery (T2-FLAIR). Extreme gradient boosting (XGBoost) was utilized for constructing the ML, clinical, and combined models. Model performance was evaluated with receiver operating characteristic (ROC) curves, decision curves, and calibration curves. Stability was evaluated using six additional classifiers. Kaplan-Meier (KM) survival analysis and the log-rank test assessed the model’s prognostic value. Results In Task 1 and Task 2, the combined model (AUC = 0.907, 0.852 and 0.830 for Task 1; AUC = 0.899, 0.895 and 0.792 for Task 2) and the optimal ML model (AUC = 0.902, 0.854 and 0.832 for Task 1; AUC = 0.904, 0.899 and 0.783 for Task 2) significantly outperformed the clinical model (AUC = 0.671, 0.656, and 0.543 for Task 1; AUC = 0.619, 0.605 and 0.400 for Task 2) in both the training, testing and validation sets. Survival analysis showed the combined model performed similarly to molecular subtype in both tasks (p = 0.964 and p = 0.746). Conclusion The multiparametric MRI ML model effectively distinguished astrocytoma, CNS WHO grade 4 from GBM, IDH-wt (WHO 2021) and differentiated astrocytoma, IDH-mut from astrocytoma, IDH-wt, CNS WHO grade 4. Additionally, the model provided reliable survival stratification for glioma patients across different molecular subtypes.https://doi.org/10.1186/s12885-025-14529-7AstrocytomaGlioblastomaMagnetic resonance imagingMachine learningMolecular subtype
spellingShingle Wenji Xu
Yangyang Li
Jie Zhang
Zhiyi Zhang
Pengxin Shen
Xiaochun Wang
Guoqiang Yang
Jiangfeng Du
Hui Zhang
Yan Tan
Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
BMC Cancer
Astrocytoma
Glioblastoma
Magnetic resonance imaging
Machine learning
Molecular subtype
title Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
title_full Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
title_fullStr Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
title_full_unstemmed Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
title_short Predicting the molecular subtypes of 2021 WHO grade 4 glioma by a multiparametric MRI-based machine learning model
title_sort predicting the molecular subtypes of 2021 who grade 4 glioma by a multiparametric mri based machine learning model
topic Astrocytoma
Glioblastoma
Magnetic resonance imaging
Machine learning
Molecular subtype
url https://doi.org/10.1186/s12885-025-14529-7
work_keys_str_mv AT wenjixu predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT yangyangli predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT jiezhang predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT zhiyizhang predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT pengxinshen predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT xiaochunwang predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT guoqiangyang predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT jiangfengdu predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT huizhang predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel
AT yantan predictingthemolecularsubtypesof2021whograde4gliomabyamultiparametricmribasedmachinelearningmodel