[1]龙治豪　连海伟　邢变枝　刘仁忠.MRI影像组学模型预测脑胶质瘤IDH-1基因突变和Ki-67表达水平的价值[J].中国临床神经外科杂志,2022,27(04):255-259.[doi:10.13798/j.issn.1009-153X.2022.04.005]
　LONG Zhi-hao,LIAN Hai-wei,XING Bian-zhi,et al.Clinical value of MRI T2WI-based radiomics model in prediction of IDH-1 genotype and Ki-67 expression level in gliomas[J].,2022,27(04):255-259.[doi:10.13798/j.issn.1009-153X.2022.04.005]
点击复制

MRI影像组学模型预测脑胶质瘤IDH-1基因突变和Ki-67表达水平的价值()
分享到：

《中国临床神经外科杂志》[ISSN:1009-153X/CN:42-1603/TN]

卷:
27
期数:
2022年04期
页码:
255-259
栏目:
论著
出版日期:
2022-04-30

文章信息/Info

Title:
Clinical value of MRI T2WI-based radiomics model in prediction of IDH-1 genotype and Ki-67 expression level in gliomas
文章编号:
1009-153X（2022）04-0255-05
作者:
龙治豪　连海伟　邢变枝　刘仁忠
430060 武汉，武汉大学人民医院神经外科（龙治豪、连海伟、刘仁忠），放射科（邢变枝）
Author(s):
LONG Zhi-hao1;  LIAN Hai-wei1;  XING Bian-zhi2;  LIU Ren-zhong1.
1. Department of Neurosurgery, Renmin Hospital of Wuhan University, Wuhan 430060, China; 2. Department of Radiology, Renmin Hospital of Wuhan University, Wuhan 430060, China
关键词:
胶质瘤; 影像组学; MRI; IDH-1; Ki-67
Keywords:
Glioma;  Radiomics;  MRI;  IDH-1;  Ki-67
分类号:
R 739.41; R 455.2
DOI:
10.13798/j.issn.1009-153X.2022.04.005
文献标志码:
A
摘要:
目的 探讨MRI影像组学模型预测脑胶质瘤IDH-1基因突变和Ki-67表达水平的价值。方法 回顾性分析2017年1月至2021年6月经术后病理证实的77例胶质瘤的临床资料，其中72例IDH-1基因检测结果完整（IDH-1组），75例Ki-67检测结果完整（Ki-67组）。基于MRI T2WI序列选择感兴趣区域，运用Python提取影像组学特征，先用两独立样本t检验进行筛选，再用LASSO回归进一步筛选特征值。使用随机森林和参数优化后的支持向量机两种分类器建立影像组学模型，绘制受试者工作特征曲线，并计算曲线下面积判断模型预测IDH-1基因突变和Ki-67表达水平的灵敏度、特异度。结果 IDH-1组t检验筛选出47个特征，再通过LASSO回归筛选出11个特征。Ki-67组t检验筛选出17个特征，再通过LASSO回归筛选出10个特征。支持向量机和随机森林两种方法建立的影像组学模型预测胶质瘤IDH-1基因突变和Ki-67表达水平均有较高的预测效能，预测准确率均超过88.0%。结论 MRI影像组学模型对预测胶质瘤IDH-1基因突变和Ki-67表达水平具有较高的应用价值，为胶质瘤术前预测提供了新思路。
Abstract:
Objective To investigate the clinical value of MRI T2WI-based radiomics model in predicting IDH-1 genotype and Ki-67 expression level in gliomas. Methods The clinical data, preoperative MRI data, and postoperative pathological data of 77 patients with glioma who underwent microsurgery from January 2017 to June 2021 were retrospectively analyzed. Of these 77 patients, 72 patients had complete IDH-1 gene data (IDH-1 group), and 75 had complete Ki-67 data (Ki-67 group). Regions of interest were selected based on the MRI T2WI images, and Python was used to extract the radiomics features and the t-test and LASSO regression were used to screen out the feature values. Two radiomics models were established using random forest and parameter-optimized support vector machine algorithms, respectively. Receiver operating characteristic curve was used to calculate the area under curve to evaluate the predictive efficacy of the two models. Results Forty-seven imaging features were screened out by t-test and then 11 imaging features were screened out by LASSO regression in IDH-1 group. Seventeen imaging features were screened out and then 10 imaging features were screened out by LASSO regression in Ki-67 group. The radiomics models established by both the support vector machine and random forest methods had high efficacy in predicting the IDH-1 gene mutation and Ki-67 expression level in gliomas, and the prediction accuracy was more than 88.0%. Conclusions MRI radiomics model has high application value in predicting IDH-1 gene mutation and Ki-67 expression level in gliomas, which can provide a new idea for preoperative assessment of gliomas.

参考文献/References:

[1] Weller M, Van Den Bent M, Preusser M, et al. EANO guide-lines on the diagnosis and treatment of diffuse gliomas of adulthood [J]. Nat Rev Clin Oncol, 2021, 18(3): 170-186.
[2] Eckel-Passow JE, Lachance DH, Molinaro AM, et al. Glio-ma groups based on 1p/19q, IDH, and TERT promoter mutations in tumors [J]. N Engl J Med, 2015, 372(26): 2499-508.
[3] Komori T. Grading of adult diffuse gliomas according to the 2021 WHO Classification of Tumors of the Central Nervous System [J]. Lab Invest, 2022, 102(2): 126-133.
[4] Wesseling P, Capper D. WHO 2016 classification of gliomas[J]. Neuropathol Appl Neurobiol, 2018, 44(2): 139-150.
[5] Su C, Jiang J, Zhang S, et al. Radiomics based on multicon-trast MRI can precisely differentiate among glioma subtypesand predict tumour-proliferative behaviour [J]. Eur Radiol, 2019, 29(4): 1986-1996.
[6] El Naqa I, Ten Haken RK. Can radiomics personaliseimmunotherapy [J]. Lancet Oncol, 2018, 19(9): 1138-1139.
[7] Yushkevich P, Piven J, Hazlett H, et al. User-guided 3Dactive contour segmentation of anatomical structures: signi-ficantly improved efficiency and reliability [J]. Neuroimage, 2006, 31(3): 1116-1128.
[8] Beesley MF, McLaren KM. Cytokeratin 19 and galectin-3 mmunohistochemistry in the differential diagnosis of solitarythyroid nodules [J]. Histopathology, 2002, 41(3): 236-243.
[9] Luo Y, Hou W, Zeng L, et al. Progress in the study of mark-ers related to glioma prognosis [J]. Eur Rev Med Pharmacol Sci, 2020, 4(14): 7690-7697.
[10] Thompson CB. Metabolic enzymes as oncogenes or tumor suppressors [J]. N Engl J Med, 2009, 360(8): 813-815.
[11] Qu Dw, Xu Hs, Han Xj, et al. Expression of cyclinD1 and Ki-67 proteins in gliomas and its clinical significance [J]. Eur Rev Med Pharmacol Sci, 2014, 18(4): 516-519.
[12] Cai J, Yang P, Zhang C, et al. ATRX mRNA expressioncombined with IDH1/2 mutational status and Ki-67 expression refines the molecular classification of astrocytic tumors: evidence from the whole transcriptome sequencing of 169 samples samples [J]. Oncotarget, 2014, 5(9): 2551-2561.
[13] Tan Y, Mu W, Wang XC, et al. Whole-tumor radiomics analysis of DKI and DTI may improve the prediction of genotypes for astrocytomas: a preliminary study [J]. Eur J Radiol, 2020, 124: 108785.
[14] Weller M, Van Den Bent M, Tonn JC, et al. EuropeanAssociation for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligoden-droglial gliomas [J]. Lancet Oncol, 2017, 18(6): e315-e329.

相似文献/References:

[1]常英男　王　策　赵天书.SOX2基因在胶质瘤中的表达及生物学作用[J].中国临床神经外科杂志,2016,(05):270.[doi:10.13798/j.issn.1009-153X.2016.05.005]
　CHANG Ying-nan,WANG Ce,ZHAO Tian-shu..Expression of SOX2 gene and its biological role in human gliomas[J].,2016,(04):270.[doi:10.13798/j.issn.1009-153X.2016.05.005]
[2]赛　克　陈忠平.胶质瘤的疗效评价[J].中国临床神经外科杂志,2016,(06):321.[doi:10.13798/j.issn.1009-153X.2016.06.001]
[3]许　耿　路俊锋　杨　忠　施建斌　吴秋月　王　烨　庄冬晓　吴劲松.神经电生理监测技术在功能区胶质瘤术中的应用[J].中国临床神经外科杂志,2016,(06):323.[doi:10.13798/j.issn.1009-153X.2016.06.002]
　XU Geng,LU Jun-feng,YANG Zhong,et al.Application of intraoperative neuroelectrophysiologic monitoring to gliomas resection in eloquent function brain regions[J].,2016,(04):323.[doi:10.13798/j.issn.1009-153X.2016.06.002]
[4]李剑峰　陈银生　赛　克　张湘衡　柯　超　杨群英　牟永告　许海雄　陈忠平.173例胶质瘤预后的影响因素分析[J].中国临床神经外科杂志,2016,(06):327.[doi:10.13798/j.issn.1009-153X.2016.06.003]
　LI Jian-feng,CHEN Yin-sheng,SAI Ke,et al.Prognostic factors for gliomas: analysis of 173 cases[J].,2016,(04):327.[doi:10.13798/j.issn.1009-153X.2016.06.003]
[5]云德波　杨宇焦　张　逵　范润金　张　渊　杜贻庆.瘤周谷氨酸、天门冬氨酸水平与胶质瘤继发性 癫痫的相关性[J].中国临床神经外科杂志,2016,(06):331.[doi:10.13798/j.issn.1009-153X.2016.06.004]
　YUN De-bo,YANG Yu-Jiao,ZHANG Kui,et al.Relationship of levels of glutamate and aspartate in peritumorous tissues with seizures in patients with gliomas[J].,2016,(04):331.[doi:10.13798/j.issn.1009-153X.2016.06.004]
[6]黄书岚　成于思　王　辉　汪超甲.FAK siRNA重组质粒的构建及其对胶质瘤U251细胞 增殖及侵袭能力的抑制作用[J].中国临床神经外科杂志,2016,(06):336.[doi:10.13798/j.issn.1009-153X.2016.06.006]
　HUANG Shu-lan,CHENG Yu-si,WANG Hui,et al.Construction of siRNA recombinant plasmid targeting focal adhesion kinase gene and its effect on the proliferation and invasiveness of human glioma U251cells[J].,2016,(04):336.[doi:10.13798/j.issn.1009-153X.2016.06.006]
[7]林　雨　张　恺　李　帅　杨学军.磁共振数字化手术单元在指导胶质瘤治疗中的作用[J].中国临床神经外科杂志,2016,(06):345.[doi:10.13798/j.issn.1009-153X.2016.06.009]
[8]戴黎明　徐成仕　王泽芬　曹长军　李志强.VEGF单抗对低氧环境下C6胶质瘤细胞侵袭性的影响[J].中国临床神经外科杂志,2016,(04):219.[doi:10.13798/j.issn.1009-153X.2016.04.009]
　DAI Li-ming,XU Cheng-shi,WANG Ze-fen,et al.Effect of nonoclonal antibody of VEGF on C6 glioma cells invasiveness under hypoxia and the role of FAK/Pyk2[J].,2016,(04):219.[doi:10.13798/j.issn.1009-153X.2016.04.009]
[9]彭泽生　田道锋　张申起　陈谦学.miR-370-3p对胶质母细胞瘤U87-MG细胞株增殖能力的影响[J].中国临床神经外科杂志,2016,(04):223.[doi:10.13798/j.issn.1009-153X.2016.04.010]
　PENG Ze-sheng,TIAN Dao-feng,ZHANG Shen-qi,et al.Effects of MircoRNA-370-3p on proliferation of glioma cell line U87-MG and its potential mechanism[J].,2016,(04):223.[doi:10.13798/j.issn.1009-153X.2016.04.010]
[10]冯　驰　郭双毅　程龙海　罗　杰.氯喹通过抑制自噬促进TRAIL诱导的胶质瘤细胞凋亡[J].中国临床神经外科杂志,2016,(04):227.[doi:10.13798/j.issn.1009-153X.2016.04.011]
　FENG Chi,GUO Shuang-yi,CHENG Long-hai,et al.Chloroquine promotes TRAIL-induced apoptosis of glioma cells through inhibition of autophagy[J].,2016,(04):227.[doi:10.13798/j.issn.1009-153X.2016.04.011]
[11]龙治豪,刘仁忠.胶质瘤中Ki-67的作用机制及影像组学的研究进展[J].中国临床神经外科杂志,2022,27(05):412.[doi:10.13798/j.issn.1009-153X.2022.05.026]

备注/Memo

备注/Memo:
通讯作者：刘仁忠，E-mail：liurenzhong@whu.edu.cn
更新日期/Last Update: 1900-01-01