Share：
Share this content in WeChat
X
[Chinese][PDF]67822
• Clinical Article •
The value of predicting the subtype of IDH mutation combining with MGMT promoter methylation in lower grade gliomas by radiomics based on preoperative MRI
SHA Yongjian  WANG Xiaochun  TAN Yan  ZHANG Hui  YANG Guoqiang 

Cite this article as: Sha YJ, Wang XC, 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.


[Abstract] Objective To develope a radiomics model to predict the subtype of isocitrate dehydrogenase mutation (IDH-mut) combining with O6-methylguanine DNA methyltransferase promoter methylation (MGMT meth) in LGGs (lower grade gliomas).Materials and Methods Preoperative MRI images, clinical and genetic information of 158 patients from the First Hospital of Shanxi Medical University, Shanxi People's Hospital and the TCGA/TCIA (The Cancer Genome Atlas and The Cancer Imaging Archive) common dataset were retrospectively collected. The above three data sets were integrated, their images were resampling and normalized, and then randomly divided into the training set and the test set in a ratio of 7∶3. A total of 1702 radiomics features of the post-contrast enhanced T1-weighted sequence (CE-T1) and the T2-weighted fluid attenuation inversion recovery sequence (T2-FLAIR) were extracted from preoperative MRI images. Feature selection was performed by single-factor logistic regression (LR), and then performed by least absolute shrinkage and selection operator (LASSO). In order to solve the shortage of minority samples and improve the universality of the model, the synthetic minority oversampling technique (SMOTE) was used to balance the training set, and then multi-factor LR was used for modeling. Finally, the performance and goodness of fit of the model was verified using receiver operating characteristic curve (ROC) and calibration curve, and a nomogram was established for visual risk prediction.Results There were no statistically significant differences in the clinical characteristics of the two subtypes in the training set and test set (P＜0.05). The area under the curve (AUC) of the radiomics model in the training set and the test set were 0.842 and 0.935, respectively, and the F-Measure were 0.965 and 0.942, respectively. The P value of the Hosmer-Lemeshow test of the calibration curve of the training set was 0.1393.Conclusions The preoperative MRI radiomics model can predict the subtype of IDH mutation combined with MGMT promoter methylation in LGGs, thus providing auxiliary guidance value for LGGs in molecular subtype diagnosis, temozolomide (TMZ) treatment decision-making and survival prediction.
[Keywords] lower grade glioma；radiomics；magnetic resonance imaging；isocitrate dehydrogenase；O6-methylguanine-DNA methyltransferase；molecular subtype

SHA Yongjian1   WANG Xiaochun2   TAN Yan2   ZHANG Hui2   YANG Guoqiang2*  

1 School of Medical Imaging, Shanxi Medical University, Taiyuan 030001, China

2 Department of Radiology, First Hospital of Shanxi Medical University, Taiyuan 030001, China

Yang GQ, E-mail: doctor_ygq@163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS National Natural Science Foundation of China (No. U21A20386, 81971592, 81971593).
Received  2022-02-13
Accepted  2022-07-01
DOI: 10.12015/issn.1674-8034.2022.07.002
Cite this article as: Sha YJ, Wang XC, 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.

[1]
Nobusawa S, Watanabe T, Kleihues P, et al. IDH1 mutations as molecular signature and predictive factor of secondary glioblastomas[J]. Clin Cancer Res, 2009, 15(19): 6002-6007. DOI: 10.1158/1078-0432.CCR-09-0715.
[2]
Louis DN, 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]
Ohgaki H, Kleihues P. The definition of primary and secondary glioblastoma[J]. Clin Cancer Res, 2013, 19(4): 764-772. DOI: 10.1158/1078-0432.CCR-12-3002.
[4]
Leu S, von Felten S, Frank S, et al. IDH/MGMT-driven molecular classification of low-grade glioma is a strong predictor for long-term survival[J]. Neuro Oncol, 2013, 15(4): 469-479. DOI: 10.1093/neuonc/nos317.
[5]
Hartmann C, Hentschel B, Wick W, et al. Patients with IDH1 wild type anaplastic astrocytomas exhibit worse prognosis than IDH1-mutated glioblastomas, and IDH1 mutation status accounts for the unfavorable prognostic effect of higher age: implications for classification of gliomas[J]. Acta Neuropathol, 2010, 120(6): 707-718. DOI: 10.1007/s00401-010-0781-z.
[6]
Wick W, Meisner C, Hentschel B, et al. Prognostic or predictive value of MGMT promoter methylation in gliomas depends on IDH1 mutation[J]. Neurology, 2013, 81(17): 1515-1522. DOI: 10.1212/WNL.0b013e3182a95680.
[7]
Lohmann P, Galldiks N, Kocher M, et al. Radiomics in neuro-oncology: Basics, workflow, and applications[J]. Methods, 2021, 188: 112-121. DOI: 10.1016/j.ymeth.2020.06.003.
[8]
Ibrahim A, Primakov S, Beuque M, et al. Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework[J]. Methods, 2021, 188: 20-29. DOI: 10.1016/j.ymeth.2020.05.022.
[9]
Liu Z, Wang S, Dong D, et al. The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges[J]. Theranostics, 2019, 9(5): 1303-1322. DOI: 10.7150/thno.30309.
[10]
van Timmeren JE, Cester D, Tanadini-Lang S, et al. Radiomics in medical imaging-"how-to" guide and critical reflection[J]. Insights Imaging, 2020, 11(1): 91. DOI: 10.1186/s13244-020-00887-2.
[11]
Avanzo M, Wei L, Stancanello J, et al. Machine and deep learning methods for radiomics[J/OL]. Med Phys, 2020, 47(5) [2022-02-13]. https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.13678. DOI: 10.1002/mp.13678.
[12]
Song J, Yin Y, Wang H, et al. A review of original articles published in the emerging field of radiomics[J/OL]. Eur J Radiol, 2020, 127 [2022-02-13]. https://linkinghub.elsevier.com/retrieve/pii/S0720048X20301807. DOI: 10.1016/j.ejrad.2020.108991.
[13]
Liu X, Li Y, Li S, et al. IDH mutation-specific radiomic signature in lower-grade gliomas[J]. Aging (Albany NY), 2019, 11(2): 673-696. DOI: 10.18632/aging.101769.
[14]
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 [2022-02-13]. https://linkinghub.elsevier.com/retrieve/pii/S0720048X1930364X. DOI: 10.1016/j.ejrad.2019.108714.
[15]
Louis DN, Perry A, Reifenberger G, et al. The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary[J]. Acta Neuropathol, 2016, 131(6): 803-820. DOI: 10.1007/s00401-016-1545-1.
[16]
Bhandari AP, Liong R, Koppen J, et al. Noninvasive Determination of IDH and 1p19q Status of Lower-grade Gliomas Using MRI Radiomics: A Systematic Review[J]. AJNR Am J Neuroradiol, 2021, 42(1): 94-101. DOI: 10.3174/ajnr.A6875.
[17]
Elreedy D, Atiya AF. A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for Handling Class Imbalance[J]. Inform Sciencess, 2019, 505: 32-64. DOI: 10.1016/j.ins.2019.07.070.
[18]
Reifenberger G, Hentschel B, Felsberg J, et al. Predictive impact of MGMT promoter methylation in glioblastoma of the elderly[J]. Int J Cancer, 2012, 131(6): 1342-1350. DOI: 10.1002/ijc.27385.
[19]
Wang J, Hu Y, Zhou X, et al. A radiomics model based on DCE-MRI and DWI may improve the prediction of estimating IDH1 mutation and angiogenesis in gliomas[J/OL]. Eur J Radiol, 2022, 147 [2022-02-13]. https://linkinghub.elsevier.com/retrieve/pii/S0720048X21006227. DOI: 10.1016/j.ejrad.2021.110141.
[20]
Manikis GC, Ioannidis GS, Siakallis L, et al. Multicenter DSC-MRI-Based Radiomics Predict IDH Mutation in Gliomas[J]. Cancers (Basel), 2021, 13(16): 3965. DOI: 10.3390/cancers13163965.
[21]
Lohmann P, Meissner A, Werner J, et al. Hybrid FET PET/MRI radiomics for the non-invasive prediction of the MGMT promoter methylation in brain tumors[J]. Nuklearmedizin, 2021, 60(2): 160. DOI: 10.1055/s-0041-1726787.
[22]
Huang H, Wang FF, Luo S, et al. Diagnostic performance of radiomics using machine learning algorithms to predict MGMT promoter methylation status in glioma patients: a meta-analysis[J]. Diagn Interv Radiol, 2021, 27(6): 716-724. DOI: 10.5152/dir.2021.21153.
[23]
Arita H, Kinoshita M, Kawaguchi A, et al. Lesion location implemented magnetic resonance imaging radiomics for predicting IDH and TERT promoter mutations in grade Ⅱ/Ⅲ gliomas[J/OL]. Sci Rep, 2018, 8(1) [2022-02-13]. https://www.nature.com/articles/s41598-018-30273-4. DOI: 10.1038/s41598-018-30273-4.
[24]
Fan Z, Sun Z, Fang S, et al. Preoperative Radiomics Analysis of 1p/19q Status in WHO Grade Ⅱ Gliomas[J/OL]. Front Oncol, 2021, 11 [2022-02-13]. https://www.frontiersin.org/articles/10.3389/fonc.2021.616740/full. DOI: 10.3389/fonc.2021.616740.
[25]
Elreedy D, Atiya AF. A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for Handling Class Imbalance[J]. Inform Sciences, 2019, 505: 32-64. DOI: 10.1016/j.ins.2019.07.070.
[26]
Fernandez A, Garcia S, Chawla NV, et al. SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary[J]. J Artif Intell Res, 2018, 61: 863-905. DOI: 10.1613/jair.1.11192.
[27]
Douzas G, Bacao F. Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE[J]. Inform Sciences, 2019, 501: 118-135. DOI: 10.1016/j.ins.2019.06.007.

PREV The value of predicting the PR expression status of meningiomas based on MRI features
NEXT Application of synthetic diffusion-weighted imaging in evaluating the grading of glioma
  


LINK


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