A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis

doi:10.1183/13993003.00775-2020

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis
	Wang, Shuo 12; Zha, Yunfei 11; Li, Weimin 10; Wu, Qingxia 9; Li, Xiaohu 8; Niu, Meng 1; Wang, Meiyun 6,7; Qiu, Xiaoming 5; Li, Hongjun 4; Yu, He 10
刊名	EUROPEAN RESPIRATORY JOURNAL
	2020-08-01
卷号	56 期号:2 页码:11
ISSN号	0903-1936
DOI	10.1183/13993003.00775-2020
通讯作者	Tian, Jie(jie.tian@ia.ac.cn)
英文摘要	Coronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19 and finding high-risk patients with worse prognosis for early prevention and medical resource optimisation is important. Here, we proposed a fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis by routinely used computed tomography. We retrospectively collected 5372 patients with computed tomography images from seven cities or provinces. Firstly, 4106 patients with computed tomography images were used to pre-train the deep learning system, making it learn lung features. Following this, 1266 patients (924 with COVID-19 (471 had follow-up for >5 days) and 342 with other pneumonia) from six cities or provinces were enrolled to train and externally validate the performance of the deep learning system. In the four external validation sets, the deep learning system achieved good performance in identifying COVID-19 from other pneumonia (AUC 0.87 and 0.88, respectively) and viral pneumonia (AUC 0.86). Moreover, the deep learning system succeeded to stratify patients into high- and low-risk groups whose hospital-stay time had significant difference (p=0.013 and p=0.014, respectively). Without human assistance, the deep learning system automatically focused on abnormal areas that showed consistent characteristics with reported radiological findings. Deep learning provides a convenient tool for fast screening of COVID-19 and identifying potential high-risk patients, which may be helpful for medical resource optimisation and early prevention before patients show severe symptoms.
资助项目	National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81871332] ; National Natural Science Foundation of China[61936013] ; National Natural Science Foundation of China[81771806] ; National Key R&D Program of China[2017YFA0205200] ; Novel Coronavirus Pneumonia Emergency Key Project of Science and Technology of Hubei Province[2020FCA015] ; Fundamental Research Funds for the Central Universities[2042020kfxg10] ; Anhui Natural Science Foundation[202004a07020003] ; Hubei Health Committee General Program[WJ2019M043] ; Anti-schistosomiasis Fund during 2019-2020[WJ2019M043] ; Beijing Municipal Commission of Health[2020-TG-002] ; Youan Medical Development Fund[BJYAYY-2020YC-03] ; China Postdoctoral Science Special Foundation[2019TQ0019] ; Crossref Funder Registry
WOS关键词	PNEUMONIA ; LUNG
WOS研究方向	Respiratory System
语种	英语
出版者	EUROPEAN RESPIRATORY SOC JOURNALS LTD
WOS记录号	WOS:000558225300003
资助机构	National Natural Science Foundation of China ; National Key R&D Program of China ; Novel Coronavirus Pneumonia Emergency Key Project of Science and Technology of Hubei Province ; Fundamental Research Funds for the Central Universities ; Anhui Natural Science Foundation ; Hubei Health Committee General Program ; Anti-schistosomiasis Fund during 2019-2020 ; Beijing Municipal Commission of Health ; Youan Medical Development Fund ; China Postdoctoral Science Special Foundation ; Crossref Funder Registry
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40442]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Tian, Jie
作者单位	1.China Med Univ, Dept Intervent Radiol, Hosp 1, Shenyang, Peoples R China 2.Xidian Univ, Engn Res Ctr Mol & Neuro Imaging, Minist Educ, Sch Life Sci & Technol, Xian, Peoples R China 3.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China 4.Capital Med Univ, Dept Radiol, Beijing Youan Hosp, Beijing, Peoples R China 5.Hubei Polytech Univ, Huangshi Cent Hosp, Dept Radiol, Edong Healthcare Grp,Affiliated Hosp, Huangshi, Hubei, Peoples R China 6.Zhengzhou Univ, Peoples Hosp, Zhengzhou, Peoples R China 7.Zhengzhou Univ, Henan Prov Peoples Hosp, Dept Med Imaging, Zhengzhou, Peoples R China 8.Anhui Med Univ, Dept Radiol, Affiliated Hosp 1, Hefei, Peoples R China 9.Northeastern Univ, Coll Med & BioMed Informat EngnVV, Shenyang, Peoples R China 10.Sichuan Univ, West China Hosp, Dept Resp & Crit Care Med, Chengdu, Sichuan, Peoples R China
推荐引用方式 GB/T 7714	Wang, Shuo,Zha, Yunfei,Li, Weimin,et al. A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis[J]. EUROPEAN RESPIRATORY JOURNAL,2020,56(2):11.
APA	Wang, Shuo.,Zha, Yunfei.,Li, Weimin.,Wu, Qingxia.,Li, Xiaohu.,...&Tian, Jie.(2020).A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis.EUROPEAN RESPIRATORY JOURNAL,56(2),11.
MLA	Wang, Shuo,et al."A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis".EUROPEAN RESPIRATORY JOURNAL 56.2(2020):11.