CT影像组学在预测肺腺癌ALK融合基因表达中的价值初探  

Preliminary value of CT radiomics in predicting anaplastic lymphoma kinase fusion gene expression in lung adenocarcinoma

作　　者：宋兰[1] 朱振宸 姜蕾 赵伦 杨青霖 隋昕[1] 杜华阳 吴焕文[4] 李霁[4] 李秀丽 宋伟[1] 金征宇[1] Song Lan;Zhu Zhenchen;Jiang Lei;Zhao Lun;Yang Qinglin;Sui Xin;Du Huayang;Wu Huanwen;Li Ji;Li Xiuli;Song Wei;Jin Zhengyu(Department of Radiology,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences,Beijing 100730,China;Deepwise Artificial Intelligence Lab,Beijing 100080,China;Department of Radiology,Yuhuangding Hospital,Yantai 264000,China;Department of Pathology,Peking Union Medical College Hospital,Chinese Academy of Medical Sciences,Beijing 100730,China)

机构地区：[1]中国医学科学院北京协和医院放射科,100730 [2]深睿医疗人工智能研究院,北京100080 [3]烟台毓璜顶医院放射科,264000 [4]中国医学科学院北京协和医院病理科,100730

出　　处：《中华放射学杂志》2019年第11期963-967,共5页Chinese Journal of Radiology

基　　金：中国医学科学院中央级公益性科研院所基本科研业务费专项项目(2018PT32003,2017PT32004)。

摘　　要：探讨CT影像组学定量特征在预测肺腺癌间变性淋巴瘤激酶(ALK)融合基因表达中的价值.方法回顾性分析2015年11月至2018年5月北京协和医院有ALK基因检测结果且术前接受本院胸部CT检查的195例肺腺癌患者(其中ALK突变患者60例).使用肺结节自动检测分割算法在CT图像上标注病变的三维容积感兴趣区(VOI).利用PyRadiomics工具对所有VOI区域进行重采样、图像预处理(包括基于小波和拉普拉斯滤波器的预处理方法)和特征提取.在Dr.Wise科研平台上对已提取的特征进行标准化处理,并分别基于不同图像预处理方式及不同特征类型筛选关键特征,用多因素logistic回归建模和10次5折交叉验证法进行验证.采用ROC评价模型对ALK基因突变的预测能力,并使用DeLong比较不同模型的效能.结果每个病灶共提取1232个影像组学特征.在特征筛选后共纳入15个组学特征建模,在训练集和验证集中模型预测ALK基因突变的AUC分别是0.88和0.78.分别基于原始CT图像、小波处理后图像和拉普拉斯高斯滤波器处理后图像的组学特征建模时,在验证集中模型的AUC分别为0.76、0.75和0.76.这3组模型与全部特征联合建模模型的效能相比差异均无统计学意义(P>0.05).以不同类型的组学特征建模,一阶特征和灰度共生矩阵(GLCM)纹理特征预测ALK基因突变能力较好,其中GLCM特征模型最优,在验证集中的AUC为0.83,准确率、敏感度和特异度分别为0.74、0.85和0.69;一阶特征模型在验证集中的AUC为0.80.结论CT影像组学定量特征在预测肺腺癌ALK融合基因表达中有较大的应用价值.Objective To explore the value of quantitative CT radiomics features in predicting the anaplastic lymphoma kinase(ALK)mutation status in lung adenocarcinoma patients.Methods This retrospective study reviewed one hundred and ninety-five lung adenocarcinoma patients(including 60 patients with ALK mutation)whose ALK genetic test results were available from Nov 2015 to May 2018 in PUMCH.VOIs were labeled by an automatic pulmonary nodule detection and segmentation algorithm and were later revised and confirmed by two senior radiologists.The PyRadiomics tools were used to resample the labeled regions,followed by image pre-processing(Wavelet filter or Laplacian of Gaussian(LoG)filter)and feature extraction.Normalized features were selected based on their representativeness on Dr.Wise research platform.Multivariate logistic regression was performed to develop prediction models of ALK mutation gene based on different image pre-processing techniques and different radiomics feature types.The results were validated by ten runs of five-fold cross validation.ROC curve analysis and Delong test were used to compare the predictive performance among models.Results Fifteen radiomics features with the highest representativeness were selected from the original 1232 features.The prediction model based on these radiomics features showed good performance(AUC=0.88 in the training set and 0.78 in the validation set)and was not significantly different from the prediction models based on radiomics features of different pre-processing images(AUC=0.76,P=0.1,original CT images;AUC=0.75,P=0.3,Wavelet-filtered images;AUC=0.76,P=0.2,LoG-filtered images).Among the models built with radiomics features of different types,the one based on GLCM feature(a subtype of texture feature)showed the best performance in predicting ALK genetic status(AUC=0.83,accuracy=0.74,sensitivity=0.85 and specificity=0.69).The model based on first-order statistic features had an AUC of 0.80.Conclusion Quantitative CT radiomics features have a good potential to anticipate t

关 键 词：肺肿瘤 影像组学 体层摄影术 X线计算机 间变性淋巴瘤激酶 

分 类 号：R73[医药卫生—肿瘤]