深度学习神经网络用于COVID-19胸部X线分类
本研究回顾性收集四家医院1384张COVID-19确诊患者(2020年3月至8月)和1024张疫情前非COVID患者的正面胸部X线片,构建基于ResNet34、ResNet50、ResNet152和VGG16集成并辅以数据增强和肺分割的深度学习分类器,在占原始图像15%(350/2326)的测试集上准确率90.3%(95%CI 86.3-93.7%)、特异度90%(95%CI 84.3-94%)、敏感度90.5%(95%CI 85-94%)、AUC 0.96(95%CI 0.93-0.97)。还实现了基于DNN图像嵌入的最近邻算法以检索相似图像。
要点
- 模型在测试集上检测COVID-19的敏感度90.5%、特异度90%、AUC 0.96。
- 集成ResNet34/50/152和VGG16并做肺分割可提升CXR分类性能。
- 基于图像嵌入的最近邻检索可找出与给定CXR影像特征最相似的历史图像。
核心结论
- 深度学习模型在胸部X线片上检测COVID-19达到准确率90.3%、敏感度90.5%、特异度90%、AUC 0.96,可辅助医疗工作并减轻医务人员负担。
研究设计与样本
- 回顾性研究,收集四家医院1384张COVID-19确诊住院患者正面胸部X线片(2020年3月至8月)和1024张疫情前非COVID患者匹配CXR,共2326张。
- 分类器为预训练DNN集成(ResNet34、ResNet50、ResNet152、VGG16),辅以数据增强和肺分割。
- 测试集为原始图像的15%(350/2326)。
- 另实现基于DNN图像嵌入的最近邻算法检索相似图像。
诊断标准与关键数值
- COVID-19阳性检测:测试集准确率90.3%(95%CI 86.3-93.7%)、特异度90%(95%CI 84.3-94%)、敏感度90.5%(95%CI 85-94%)、AUC 0.96(95%CI 0.93-0.97)。
临床应用与阅片要点
- 可将CXR深度学习分类作为COVID-19筛查辅助工具,帮助减少医务人员阅片工作量。
- 相似图像检索工具可依据模型图像嵌入找到影像特征相近的既往CXR供对比参考。
局限性
- 回顾性研究设计。
- 测试集仅占原始图像的15%(350/2326)。
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
OBJECTIVES: In the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model's results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals.
METHODS: In this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image.
RESULTS: Our model achieved accuracy of 90.3%, (95% CI: 86.3-93.7%) specificity of 90% (95% CI: 84.3-94%), and sensitivity of 90.5% (95% CI: 85-94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93-0.97).
CONCLUSION: We provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19.
KEY POINTS: • A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%. • A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model's image embeddings.
引用
- Keidar D, Yaron D, Goldstein E, et al. COVID-19 classification of X-ray images using deep neural networks. Eur Radiol. 2021. PMID: 34052882. doi:10.1007/s00330-021-08050-1
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。