基于双参数MRI影像组学构建的支持向量机模型对乳腺癌人表皮生长因子受体-2和激素受体表达的预测效能  

Efficacy of support vector machine model constructed based on dual-parameter MRI radiomics in predicting the expression of human epidermal growth factor receptor-2 and hormone receptor in breast cancer patients

作　　者：侯慧 朱银杏 王太宇 张翼[2] 刘志鹏[2] HOU Hui;ZHU Yinxing;WANG Taiyu;ZHANG Yi;LIU Zhipeng(Department of Imaging,the Fourth People′s Hospital of Taizhou in Jiangsu Province,Taizhou,Jiangsu,225300;Department of Information,Taizhou People′s Hospital Affiliated to Nanjing Medical University,Taizhou,Jiangsu,225300;Department of Thyroid and Breast Surgery,Taizhou Hospital of Traditional Chinese Medicine in Jiangsu Province,Taizhou,Jiangsu,225300)

机构地区：[1]江苏省泰州市第四人民医院影像科,江苏泰州225300 [2]南京医科大学附属泰州人民医院信息科,江苏泰州225300 [3]江苏省泰州市中医院甲乳外科,江苏泰州225300

出　　处：《实用临床医药杂志》2024年第4期7-13,共7页Journal of Clinical Medicine in Practice

基　　金：南京医科大学泰州临床医学院博士后科研资助项目(TZBSHKY202204);江苏省泰州市中医药科技发展项目(TZ202301)。

摘　　要：目的构建基于磁共振T_(2)WI反转恢复压脂(TIRM)及扩散加权成像(DWI)序列图像的支持向量机(SVM)模型,评估其对乳腺癌人表皮生长因子受体-2(HER-2)和激素受体(HR)表达水平的预测效能。方法收集128个于术前或治疗前接受乳腺MRI检查的乳腺癌病灶。根据免疫组织化学(IHC)或原位荧光杂交(FISH)检测结果进行分组。使用ITK-SNAP软件在磁共振TIRM和DWI序列图像上勾画三维容积感兴趣区(VOI),并导入Pyradiomics程序提取影像组学特征。对数据进行归一化处理后使用基于支持向量机的递归特征消除法(SVM-RFE)筛选特征。采用随机分层抽样方法将108例病例按照8∶2比例分为训练组及验证组,另外20例作为外部测试组。采用SVM机器学习分类器构建影像组学模型。采用受试者工作特征(ROC)曲线评估模型预测效能。采用DeLong检验评估各影像组学模型ROC曲线下面积(AUC)。采用SHAP算法进行可视化分析,并筛选最具贡献力的预测特征。结果联合模型(训练组AUC=0.94;验证组AUC=0.90)对HER-2的预测效能均高于TIRM模型(训练组AUC=0.85;验证组AUC=0.80)、单DWI模型(训练组AUC=0.88;验证组AUC=0.66)。外部测试组联合模型的AUC为0.89。SHAP算法得出DWI序列的特征贡献较大。基于TIRM和DWI序列联合特征(训练组AUC=0.96;验证组AUC=0.88)、单DWI序列特征(训练组AUC=0.92;验证组AUC=0.86)构建的影像组学模型预测HR效能优于单TIRM序列特征(训练组AUC=0.84;验证组AUC=0.68)构建的模型。外部测试组证明联合模型具有较好的预测效能,AUC为0.90。SHAP算法得出TIRM序列的特征贡献较大。结论基于磁共振成像TIRM和DWI序列联合特征构建的影像组学模型对于HER-2水平具有良好的预测效能,对HR表达具有较大的预测潜力,可为乳腺癌患者制订个性化治疗方案提供依据。Objective To construct a support vector machine(SVM) model based on magnetic resonance imaging(MRI) T_(2WI) turbo inversion recovery magnitude(TIRM) and diffusion-weighted imaging(DWI) sequences,and evaluate its predictive performance for expression levels of human epidermal growth factor receptor-2(HER-2) and hormone receptor(HR) in breast cancer.Methods A total of 128 breast cancer lesions underwent breast MRI before surgery or treatment were collected,and were grouped according to immunohistochemical(IHC) method or in situ fluorescence hybridization(FISH)results.ITK-SNAP software was used to outline the three-dimensional volume region of interest( VOI)on magnetic resonance TIRM and DWI sequence images,and Pyradiomics program was introduced to extract the image omics features.After normalization of the data,a recursive feature elimination method based on support vector machine-recursive feature elimination( SVM-RFE) was used to filter the features.A total of 108 cases were divided into training group and verification group according to8∶ 2 ratio by random stratified sampling method,and the other 20 cases were used as external test group.SVM machine learning classifier was used to construct the image omics model.Receiver operating characteristic( ROC) curve was used to evaluate the prediction efficiency of the model.DeLong test was used to evaluate the area under the curve( AUC) of each image omics model.SHAP algorithm was used for visual analysis,and the most contributing prediction features were screened.Results The prediction efficiency of the combined model( training group AUC = 0.94,verification group AUC = 0.90) for HER-2 was higher than that of TIRM model( training group AUC = 0.85,verification group AUC = 0.80) and single DWI model( training group AUC = 0.88,verification group AUC = 0.66).The AUC of combined model in the external test group was 0.89.The feature contribution of DWI sequence obtained by SHAP algorithm was great.The image omics model based on the combination of TIRM and DWI sequence featu

关 键 词：影像组学 乳腺癌 支持向量机 人表皮生长因子受体-2 激素受体 

分 类 号：R737.9[医药卫生—肿瘤] R445.2[医药卫生—临床医学] R319