Share：
Share this content in WeChat
X
[Chinese][PDF]4805
• Clinical Article •
Prediction of habitat subregions of the glioblastoma microenvironment based on multimodal MRI radiomics for MGMT promoter methylation expression
JIAO Kaijian  YANG Bo  CHEN Wen  FANG Yuhui  CHEN Yalin  WU Lei 

Cite this article as: JIAO K J, YANG B, CHEN W, et al. Prediction of habitat subregions of the glioblastoma microenvironment based on multimodal MRI radiomics for MGMT promoter methylation expression[J]. Chin J Magn Reson Imaging, 2023, 14(11): 25-30, 76. DOI:10.12015/issn.1674-8034.2023.11.005.


[Abstract] Objective To explore the efficacy of multimodal imaging radiomics models of different tumor microenvironment subregions in predicting the methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) promoter in glioblastoma before surgery.Materials and Methods A retrospective analysis was conducted on preoperative MRI images, clinical, and genetic information of 600 glioblastoma patients from Taihe Hospital, Hubei University of Medicine, University of Pennsylvania, and University of California, San Francisco. The preprocessed images were automatically segmented to obtain three subregions of the tumor microenvironment. From the preoperative MRI images [contrast enhanced T1-weighted imaging (T1WI-CE), T2 fluid attenuation inversion recovery (T2-FLAIR) sequence, and diffusion tensor imaging (DTI) fractional anisotropy (FA) maps], 2 153 radiomics features were extracted from three habitat subregions, including enhanced region, necrotic region and edema region. Feature selection was performed using correlation analysis, minimum redundancy maximum relevance (MRMR), and Boruta algorithm, and the XGBoost algorithm was used to build classification model. The diagnostic performance of the models was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), accuracy, sensitivity, specificity, and DeLong test for model comparison.Results There were no statistically significant differences in the intergroup comparisons of clinical features between the two subtypes in the training and testing sets (P＞0.05). The multimodal imaging radiomics model for the enhanced region had AUCs of 0.842 and 0.935 in the training and validation sets, respectively. Ten features from the multimodal habitat subregions were obtained after feature selection. The AUC of the imaging omics model in the multimodal habitat subregion was 0.874 and 0.899 on the training and test sets, respectively.Conclusions The preoperative MRI radiomics models can predict the MGMT promoter methylation status in glioblastoma patients, and the multimodal combination models showed more robust diagnostic performance. The study of tumor microenvironment subregions provides important clinical utility for accurate molecular subtyping, decision-making for temozolomide (TMZ) use, and survival prediction in glioblastoma patients.
[Keywords] glioblastoma；radiomics；magnetic resonance imaging；O6-methylguanine-DNA methyltransferase promoter；habitat imaging

JIAO Kaijian1, 2   YANG Bo1, 2   CHEN Wen1, 2   FANG Yuhui1   CHEN Yalin1   WU Lei2*  

1 School of Biomedical Engineering Hubei University of Medicine, Shiyan 442000, China

2 Institute of Medical Imaging, Medical Imaging Center, Taihe Hospital, Hubei University of Medicine, Shiyan 442000, China

Corresponding author: WU L, E-mail: cookiebag@163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Nature Science Foundation of Hubei Province (No. 2022CFB853); Wu Jieping Medical Foundation Special Fund for Clinical Research (No. 320.6750.2020-08-6).
Received  2023-08-02
Accepted  2023-11-07
DOI: 10.12015/issn.1674-8034.2023.11.005
Cite this article as: JIAO K J, YANG B, CHEN W, et al. Prediction of habitat subregions of the glioblastoma microenvironment based on multimodal MRI radiomics for MGMT promoter methylation expression[J]. Chin J Magn Reson Imaging, 2023, 14(11): 25-30, 76. DOI:10.12015/issn.1674-8034.2023.11.005.

[1]
OSTROM Q T, PRICE M, NEFF C, et al. CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2015-2019[J/OL]. Neuro Oncol, 2022, 24(Suppl 5): v1-v95 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/36196752/. DOI: 10.1093/neuonc/noac202.
[2]
LOUIS D N, PERRY A, WESSELING P, et al. The 2021 WHO Classification of Tumors of the Central Nervous System: A summary[J]. Neuro Oncol, 2021, 23(8): 1231-1251. DOI: 10.1093/neuonc/noab106.
[3]
TOMAR M S, KUMAR A, SRIVASTAVA C, et al. Elucidating the mechanisms of Temozolomide resistance in gliomas and the strategies to overcome the resistance[J/OL]. Biochim Biophys Acta Rev Cancer, 2021, 1876(2): 188616 [2023-08-02]. DOI: 10.1016/j.bbcan.2021.188616.
[4]
TORRE M, WEN P Y, IORGULESCU J B. The predictive value of partial MGMT promoter methylation for IDH-wild-type glioblastoma patients[J]. Neurooncol Pract, 2023, 10(2): 126-131. DOI: 10.1093/nop/npac070.
[5]
DELLA MONICA R, CUOMO M, BUONAIUTO M, et al. MGMT and whole-genome DNA methylation impacts on diagnosis, prognosis and therapy of glioblastoma multiforme[J/OL]. Int J Mol Sci, 2022, 23(13): 7148 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/35806153/. DOI: 10.3390/ijms23137148.
[6]
JIMENEZ V G, DOVAL M B, BELLVERT C G, et al. Quantitative analysis of MGMT promoter methylation status changes by pyrosequencing in recurrent glioblastoma[J/OL]. Neuropathology, 2022 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/36504469/. DOI: 10.1111/neup.12887.
[7]
HANEBERG A G, PIERRE K, WINTER-REINHOLD E, et al. Introduction to radiomics and artificial intelligence: A primer for radiologists[J]. Semin Roentgenol, 2023, 58(2): 152-157. DOI: 10.1053/j.ro.2023.02.002.
[8]
LI Z C, BAI H, SUN Q, et al. Multiregional radiomics features from multiparametric MRI for prediction of MGMT methylation status in glioblastoma multiforme: A multicentre study[J]. Eur Radiol, 2018, 28(9): 3640-3650. DOI: 10.1007/s00330-017-5302-1.
[9]
JIANG C, KONG Z, LIU S, et al. Fusion radiomics features from conventional MRI predict MGMT promoter methylation status in lower grade gliomas[J/OL]. Eur J Radiol, 2019, 121: 108714 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/31704598/. DOI: 10.1016/j.ejrad.2019.108714.
[10]
SASAKI T, KINOSHITA M, FUJITA K, et al. Radiomics and MGMT promoter methylation for prognostication of newly diagnosed glioblastoma[J/OL]. Sci Rep, 2019, 9(1): 14435 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/31594994/. DOI: 10.1038/s41598-019-50849-y.
[11]
LI Z C, BAI H, SUN Q, et al. Multiregional radiomics profiling from multiparametric MRI: Identifying an imaging predictor of IDH1 mutation status in glioblastoma[J]. Cancer Med, 2018, 7(12): 5999-6009. DOI: 10.1002/cam4.1863.
[12]
WEI J, YANG G, HAO X, et al. A multi-sequence and habitat-based MRI radiomics signature for preoperative prediction of MGMT promoter methylation in astrocytomas with prognostic implication[J]. Eur Radiol, 2019, 29(2): 877-888. DOI: 10.1007/s00330-018-5575-z.
[13]
BAKAS S, SAKO C, AKBARI H, et al. The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics[J/OL]. Sci Data, 2022, 9(1): 453 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/35906241/. DOI: 10.1038/s41597-022-01560-7.
[14]
CALABRESE E, VILLANUEVA-MEYER J E, RUDIE J D, et al. The University of California San Francisco Preoperative Diffuse Glioma MRI Dataset[J/OL]. Radiol Artif Intell, 2022, 4(6): e220058 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/36523646/. DOI: 10.1148/ryai.220058.
[15]
ISENSEE F, JÄGER P F, FULL P M, et al. nnU-net for Brain Tumor Segmentation[C]. In: International MICCAI Brainlesion Workshop. Springer, Cham, 2020, 12659: 118-132[2023-08-02]. https://doi.org/10.1007/978-3-030-72087-2_11. DOI: 10.1007/978-3-030-72087-2_11.
[16]
MCKINLEY R, REBSAMEN M, DÄTWYLER K, et al. Uncertainty-Driven Refinement of Tumor-Core Segmentation Using 3D-to-2D Networks with Label Uncertainty[C]. In: International MICCAI Brainlesion Workshop. Springer, Cham, 2021, 12658: 401-411[2023-08-02]. https://link.springer.com/chapter/10.1007/978-3-030-72084-1_36. DOI: 10.1007/978-3-030-72084-1_36.
[17]
BAID U, GHODASARA S, BILELLO M, et al. The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification[J/OL]. ArXiv, 2021: 2107.02314 [2023-08-02]. https://arxiv.org/abs/2107.02314v1. DOI: 10.48550/arXiv.2107.02314.
[18]
KURSA M B, RUDNICKI W R. Feature selection with the Boruta package[J]. J Stat Softw, 2010, 36(11): 1-13. DOI: 10.18637/jss.v036.i11.
[19]
CHEN T, GUESTRIN C. XGBoost: A scalable tree boosting system[J/OL]. ArXiv, 2016: 1603.02754 [2023-08-02]. https://arxiv.org/abs/1603.02754. DOI: 10.48550/arXiv.1603.02754.
[20]
BAKAS S, REYES M, BATTISTELLA E, et al. Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge[Z]. 2018
[21]
VERMA R, CORREA R, HILL V B, et al. Tumor habitat-derived radiomic features at pretreatment MRI that are prognostic for progression-free survival in glioblastoma are associated with key morphologic attributes at histopathologic examination: A feasibility study[J/OL]. Radiol Artif Intell, 2020, 2(6): e190168 [2023-08-02]. https://pubs.rsna.org/doi/10.1148/ryai.2020190168. DOI: 10.1148/ryai.2020190168.
[22]
VERMA R, HILL V B, STATSEVYCH V, et al. Stable and discriminatory radiomic features from the tumor and its habitat associated with progression-free survival in glioblastoma: A multi-institutional study[J]. AJNR Am J Neuroradiol, 2022, 43(8): 1115-1123. DOI: 10.3174/ajnr.A7591.
[23]
KURSA M B. Robustness of random forest-based gene selection methods[J/OL]. BMC Bioinformatics, 2014, 15(1): 8 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/24410865/. DOI: 10.1186/1471-2105-15-8.
[24]
SHA Y, YAN Q, TAN Y, et al. Prediction of the molecular subtype of IDH mutation combined with MGMT promoter methylation in gliomas via radiomics based on preoperative MRI[J/OL]. Cancers, 2023, 15(5): 1440 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/36900232/. DOI: 10.3390/cancers15051440.
[25]
WEI W, CUI L, XIE L Z, et al. MR-based radiomics method for prediction of MGMT promoter methylation in glioblastoma[J]. Diagnostic Imaging & Interventional Radiology, 2018, 27(3): 179-184. DOI: 10.3969/j.issn.1005-8001.2018.03.001.
[26]
WANG G, ZHAO J J, NUERBIYEMU·A B L K M, et al. Study on the effectiveness of subregion MRI radiomic combined with classification algorthm to predicting MGMT methylation in glioblastoma[J]. J Clin Radiol, 2022, 41(7): 1222-1226. DOI: 10.13437/j.cnki.jcr.2022.07.034.
[27]
XI Y B, GUO F, XU Z L, et al. Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma[J]. J Magn Reson Imaging, 2018, 47(5): 1380-1387. DOI: 10.1002/jmri.25860.
[28]
ZHANG X Y, LIU G L, ZHANG J, et al. Prediction of the expression of MGMT promoter methylation in IDH wild-type glioblastoma via multiparametric MRI radiomics[J]. Chin J Med Imaging, 2023, 31(5): 433-441. DOI: 10.3969/j.issn.1005-5185.2023.05.001.
[29]
SHA Y J, WANG X C, TAN Y, et al. The value of predicting the subtype of IDH mutation combining with MGMT promoter methylation in lower grade gliomas by radiomics based on preoperative MRI[J]. Chin J Magn Reson Imaging, 2022, 13(7): 6-11. DOI: 10.12015/issn.1674-8034.2022.07.002.
[30]
CHEN S X, XU Y, YE M P, et al. Prediction of MGMT promoter methylation in gliomas with different radiomics models based on MRI[J]. Chin J Magn Reson Imaging, 2022, 13(3): 1-5, 36. DOI: 10.12015/issn.1674-8034.2022.03.001.
[31]
XUE C Q, DU X H, JIN L, et al. Prediction of methylation status of MGMT promoter in WHO grade Ⅱ, Ⅲ glioma based on MRI deep learning model[J]. Chin J Radiol, 2021, 55(7): 734-738. DOI: 10.3760/cma.j.cn112149-20200825-01029.
[32]
CALABRESE E, RUDIE J D, RAUSCHECKER A M, et al. Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma[J/OL]. Neurooncol Adv, 2022, 4(1): vdac060 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/35611269/. DOI: 10.1093/noajnl/vdac060.
[33]
ROBINET L, SIEGFRIED A, ROQUES M, et al. MRI-based deep learning tools for MGMT promoter methylation detection: A thorough evaluation[J/OL]. Cancers, 2023, 15(8): 2253 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/37190181/. DOI: 10.3390/cancers15082253.
[34]
SAXENA S, JENA B, MOHAPATRA B, et al. Fused deep learning paradigm for the prediction of o6-methylguanine-DNA methyltransferase genotype in glioblastoma patients: A neuro-oncological investigation[J/OL]. Comput Biol Med, 2023, 153: 106492 [2023-08-02]. https://pubmed.ncbi.nlm.nih.gov/36621191/. DOI: 10.1016/j.compbiomed.2022.106492.

PREV Application of compressed sensing combined with EPI-ASL technology in ischemic stroke
NEXT Myocardial fibrosis by late gadolinium enhancement-cardiovascular magnetic resonance and adverse outcomes in patients with hypertrophic cardiomyopathy: A Meta-analysis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn