基于深度学习卷积神经网络的肺结核CT诊断模型效能初探

A preliminary investigation on a deep learning convolutional neural networks based pulmonary tuberculosis CT diagnostic model

目的评价基于深度学习卷积神经网络(convolutional neural networks,CNN)的肺结核CT辅助诊断模型在临床中的应用价值。方法收集2017年3月至2018年3月河北省胸科医院影像科菌阳并接受胸部高分辨率CT平扫检查的1764例患者的病例资料,其中男937例,女827例,年龄17~73岁,平均年龄38.4岁。由4名影像科医师对含病变的20139幅CT图像进行分类标注(17种影像特征),以此作为训练数据集,构建肺结核CT图像CNN诊断模型。训练数据集数量最多的前5种影像特征依次为:浸润型肺结核、空洞型肺结核、胸膜增厚、干酪性肺炎和胸腔积液。从已标注图像中随机抽取302幅图像作为测试数据集,以2名高级职称医师的诊断为“金标准”,比较CNN诊断模型和医师在肺结核CT诊断中敏感度和准确率的差异,统计CNN诊断模型分类错误的类型、数量,并绘制自由响应受试者工作特征(FROC)曲线,以测量该模型的最大诊断效能。结果CNN诊断模型对测试数据集中浸润型肺结核、空洞型肺结核、胸膜增厚、干酪性肺炎和胸腔积液的诊断准确率分别为:95.33%(10982/11520)、73.68%(2151/2920)、73.07%(1128/1544)、83.33%(1020/1225)和94.11%(814/865);CNN诊断模型的总体诊断敏感度和准确率分别为95.49%(339/355)和90.40%(339/375),医师的对应数值分别为:93.80%(348/371)和92.80%(348/375),CNN模型和医师诊断比较差异无统计学意义(敏感度χ^(2)=1.022,P=0.312;准确率χ^(2)=1.404,P=0.236);FROC曲线显示,当敏感度为78%,假阳性区域个数为2.48时,该模型诊断效能最大。CNN诊断模型诊断结核病变的分类错误主要集中于纤维条索灶、空洞型肺结核、干酪性肺炎与浸润型肺结核的混淆上。结论基于深度学习CNN的肺结核CT辅助诊断模型有较高的诊断敏感度和准确率,该模型可辅助影像科医师的肺结核诊断工作,值得在临床工作中推广应用。

Objective To evaluate the clinical value of a pulmonary tuberculosis CT diagnostic model based on deep learning convolutional neural networks(CNN).Methods From March 2017 to March 2018,a total of 1764 patients with positive sputum for tuberculous bacterium and had received high-resolution chest CT scan in radiology department of Hebei province chest hospital were enrolled.Among them,937 were male,and 827 were female,aging from 17-73 years(average 38.4).A total of 20139 CT images(17 kinds of image features)classified by 4 radiologists were used as training dataset to create a tuberculosis CT CNN diagnostic model.The top 5 image features in training set were:infiltrative pulmonary tuberculosis,cavitary pulmonary tuberculosis,pleural thickening,caseous pneumonia and pleural effusion.A total of 302 images were randomly selected from the marked images as testing dataset.The diagnosis of 2 senior radiologists was taken as“golden standard”.The differences of sensitivity and accuracy in CT diagnosis between the CNN diagnostic model and the radiologists were compared.The classification error types and numbers of the CNN diagnostic model were recorded.FROC(free response operating characteristic curve)curve was drawn and the highest diagnostic efficiency of the model was measured.Results The diagnostic accuracy of infiltrative pulmonary tuberculosis,cavitary pulmonary tuberculosis,pleural thickening,caseous pneumonia and pleural effusion by the CNN diagnostic model were 95.33%(10982/11520),73.68%(2151/2920),73.07%(1128/1544),83.33%(1020/1225)and 94.11%(814/865),respectively.The overall diagnostic sensitivity and accuracy of the CNN model were 95.49%(339/355)and 90.40%(339/375),respectively,and the corresponding values of radiologists were 93.80%(348/371)and 92.80%(348/375),respectively,and there was no statistical difference between the CNN model and the radiologists(sensitivity χ^(2)=1.022,P=0.312;accuracy χ^(2)=1.404,P=0.236).FROC curve showed that when sensitivity of the CNN model was 78%and FPI value was 2.48,it reached the highest diagnostic efficiency.The classification error of CNN diagnostic models was mainly confusion of fiber stripe components,cavitary pulmonary tuberculosis,caseous pneumonia and infiltrative pulmonary tuberculosis.Conclusions The CNN-based pulmonary tuberculosis CT diagnostic model exhibited high sensitivity and accuracy(95.49%and 90.40%respectively).It could assist radiologists in CT diagnosis of pulmonary tuberculosis and deserve further clinical application.