胸部X线摄影中的深度学习:使用卷积神经网络自动分类肺结核
本研究使用1007张后前位胸部X线片,按68.0%训练、17.1%验证、14.9%测试划分,采用AlexNet和GoogLeNet两种深度卷积神经网络区分肺结核表现与健康,最佳集成分类器AUC达0.99;分类器分歧的13例经心胸放射科医师盲法判读全部正确,放射科医师辅助流程敏感度97.3%、特异度100%。
要点
- AlexNet与GoogLeNet集成分类器在测试集上AUC达0.99,可准确分类肺结核与健康胸片。
- 分类器分歧的13/150例测试病例经放射科医师盲法判读全部正确,辅助流程敏感度97.3%、特异度100%。
- 预训练模型AUC高于未训练模型(P < .001),数据增强进一步提升准确率(AlexNet P = .03,GoogLeNet P = .02)。
核心结论
- 深度卷积神经网络可在胸部X线摄影上准确分类肺结核,最佳集成分类器AUC为0.99;分类器分歧病例经放射科医师辅助判读可进一步提高准确率。
研究设计与样本
- 研究使用4个去标识化、符合HIPAA的数据集,共1007张后前位胸部X线片,免于机构审查委员会审查;数据集按训练68.0%、验证17.1%、测试14.9%划分;采用AlexNet和GoogLeNet两种深度卷积神经网络,使用未训练及ImageNet预训练网络,并进行多种预处理技术增强,对最佳性能算法进行集成;分类器分歧病例由一名独立委员会认证的心胸放射科医师盲法判读。
诊断标准与关键数值
- 最佳性能分类器为AlexNet与GoogLeNet深度卷积神经网络的集成,AUC为0.99;预训练模型AUC高于未训练模型(P < .001);数据增强进一步提高准确率(AlexNet P = .03,GoogLeNet P = .02);测试集150例中分类器分歧13例,经心胸放射科医师盲法判读全部正确(100%);放射科医师辅助流程敏感度97.3%、特异度100%。
临床应用与阅片要点
- 原文结论指出,深度卷积神经网络可在胸部X线摄影上准确分类肺结核;对于分类器之间存在分歧的病例,采用放射科医师辅助判读的流程进一步提高了准确率。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
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 board-certified 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. © RSNA, 2017.
引用
- Lakhani P, Sundaram B. Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks. Radiology. 2017. PMID: 28436741. doi:10.1148/radiol.2017162326
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。