机构：[1]Key Laboratory of Ministry of Industry and Information, Technology of Biomedical Engineering and Translational Medicine, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[2]Translational Medical Research Center, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[3]HKU Business School, The University of Hong Kong, Hong Kong, People’s Republic of China.[4]Department of Critical Care Medicine, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, People’s Republic of China.首都医科大学附属天坛医院[5]Department of Medical Imaging, Suizhou Hospital, Hubei University of Medicine (Suizhou Central Hospital), Suizhou 431300, Hubei, People’s Republic of China.[6]Department of Radiology, Wuhan Third Hospital, Tongren Hospital of Wuhan University, Wuhan 430063, Hubei, People’s Republic of China.[7]Department of Radiology, WenZhou Central Hospital, WenZhou 325000, Zhejiang, People’s Republic of China.[8]Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, People’s Republic of China.首都医科大学附属天坛医院[9]Pulmonary and Critical Care Medicine, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[10]Department of Radiology, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[11]Department of Radiology, Xiantao First People’s Hospital, Affiliated to Yangtze University, Xiantao 433000, Hubei, People’s Republic of China.[12]Department of Radiology, The First People’s Hospital of Jiangxia District, Wuhan 430200, Hubei, People’s Republic of China.[13]Department of Radiology, Wuhan Jinyintan Hospital, Wuhan 430040, Hubei, People’s Republic of China.[14]Department of Medical Imaging, Affiliated Hospital of Putian University, Putian 351100, Fujian, People’s Republic of China.[15]Department of Radiology, Chengdu Public Health Clinical Medical Center, Chengdu 610061, Sichuan, People’s Republic of China.[16]Department of Radiology, Wuhan Huangpi People’s Hospital, Wuhan 430300, Hubei, People’s Republic of China.[17]Jianghan University Affiliated Huangpi People’s Hospital, Wuhan 430300, Hubei, People’s Republic of China.[18]Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, People’s Republic of China.首都医科大学附属天坛医院[19]Department of Medical Imaging Center, Dazhou Central Hospital, Dazhou 635000, Sichuan, People’s Republic of China.[20]Department of Radiology, Beijing Daxing District People’s Hospital (Capital Medical University Daxing Teaching Hospital), Beijing 100191, People’s Republic of China.[21]Department of Radiology, Shaoxing People’s Hospital (The First Affiliated Hospital of Shaoxing University), Shaoxing 312000, Zhejiang, People’s Republic of China.[22]Department of Radiology, The People’s Hospital of Zigui, Zigui 443600, Hubei, People’s Republic of China.[23]Department of Medical Imaging, Anshan Central Hospital, Anshan 114001, Liaoning, People’s Republic of China.[24]Department of Medical Imaging, Guizhou Provincial People’s Hospital, Guiyang 550002, Guizhou, People’s Republic of China.[25]Department of Computer Application and Management, Chinese PLA General Hospital, Beijing 100070, People’s Republic of China.[26]Department of Automation, Tsinghua University, Beijing 100084, People’s Republic of China.[27]China National Clinical Research Center for Neurological Diseases, Center for Bigdata Analytics and Artificial Intelligence, Beijing 100070, People’s Republic of China.[28]Biomind Technology Co. Ltd, Beijing 101300, People’s Republic of China.[29]Department of Radiology, 5th Medical Center, Chinese PLA General Hospital, Beijing 100039, People’s Republic of China.
The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.
基金：
This study was supported by the National Key Research and Development Program [2017YFC0114001].
第一作者机构：[1]Key Laboratory of Ministry of Industry and Information, Technology of Biomedical Engineering and Translational Medicine, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[2]Translational Medical Research Center, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.
共同第一作者：
通讯作者：
通讯机构：[1]Key Laboratory of Ministry of Industry and Information, Technology of Biomedical Engineering and Translational Medicine, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.[2]Translational Medical Research Center, Chinese PLA General Hospital, Beijing 100853, People’s Republic of China.
推荐引用方式(GB/T 7714)：
Liu Bohan,Liu Pan,Dai Lutao,et al.Assisting scalable diagnosis automatically via CT images in the combat against COVID-19[J].SCIENTIFIC REPORTS.2021,11(1):doi:10.1038/s41598-021-83424-5.
APA：
Liu, Bohan,Liu, Pan,Dai, Lutao,Yang, Yanlin,Xie, Peng...&He, Kunlun.(2021).Assisting scalable diagnosis automatically via CT images in the combat against COVID-19.SCIENTIFIC REPORTS,11,(1)
MLA：
Liu, Bohan,et al."Assisting scalable diagnosis automatically via CT images in the combat against COVID-19".SCIENTIFIC REPORTS 11..1(2021)
