Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks
Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks
复制标题
DOI：
10.1148/radiol.2017162326
复制
发表时间：
2017-08-01
期刊：
影响因子：
19.7
通讯作者：
Sundaram, Baskaran
中科院分区：
文献类型：
--
作者：
Lakhani, Paras;Sundaram, Baskaran
目的：为了评估深度卷积神经网络（DCNN）检测肺结核（TB）的胸部X线片的有效性，材料和方法：本研究中使用了四个去识别的符合HIPAA的数据集，这些数据集由1007张后前位胸片组成，免于机构审查委员会的审查。数据集分为训练（68.0%），验证（17.1%）和测试（14.9%）。两种不同的DCNN，AlexNet和GoogLeNet，用于将图像分类为具有肺结核的表现或健康。使用ImageNet上未经训练和预训练的网络，并使用多种预处理技术进行增强。对性能最佳的算法进行了集成。对于分类器不一致的情况，独立的委员会认证的心胸放射科医生盲解图像，以评估潜在的放射科医生增强工作流程。受试者工作特征曲线和曲线下面积（AUC）被用来评估模型的性能，通过使用德隆方法的统计比较的受试者工作特征currents.Results：表现最好的分类器有一个AUC为0.99，这是一个集成的AlexNet和GoogLeNet DCNN。预训练模型的AUC大于未训练模型的AUC（P < .001）。增加数据集进一步提高了准确性（AlexNet和GoogLeNet的P值分别为.03和.02）。DCNN在150个测试病例中的13个中存在分歧，这些病例由心胸放射科医生盲审，他们正确解释了所有13个病例（100%）。这种放射学家增强的方法的灵敏度为97.3%，特异性为100%。结论：使用DCNN的深度学习可以在胸部X线摄影中准确分类TB，AUC为0.99。一个放射科医生增强的方法的情况下，有分歧的分类进一步提高准确性。
Purpose: To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs.Materials and Methods: Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent boardcertified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves.Results: The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were.03 and.02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%.Conclusion: Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy.