AI detection of mild COVID-19 pneumonia from chest CT scans

doi:10.1007/s00330-021-07797-x

	AI detection of mild COVID-19 pneumonia from chest CT scans
	Yao, Jin-Cao 2,3; Wang, Tao 4; Hou, Guang-Hua 5; Ou, Di 2,3; Li, Wei 2,3; Zhu, Qiao-Dan 2,3; Chen, Wen-Cong 1; Yang, Chen 2,3; Wang, Li-Jing 2,3; Wang, Li-Ping 2,3
刊名	EUROPEAN RADIOLOGY
	2021-03-18
关键词	Computer-assisted diagnosis Volume CT COVID-19 Artificial intelligence Deep learning
ISSN号	0938-7994
DOI	10.1007/s00330-021-07797-x
通讯作者	Xu, Dong(xudong@zjcc.org.cn) ; Li, Ya-Qing(yaqing_li@163.com)
英文摘要	Objectives An artificial intelligence model was adopted to identify mild COVID-19 pneumonia from computed tomography (CT) volumes, and its diagnostic performance was then evaluated. Methods In this retrospective multicenter study, an atrous convolution-based deep learning model was established for the computer-assisted diagnosis of mild COVID-19 pneumonia. The dataset included 2087 chest CT exams collected from four hospitals between 1 January 2019 and 31 May 2020. The true positive rate, true negative rate, receiver operating characteristic curve, area under the curve (AUC) and convolutional feature map were used to evaluate the model. Results The proposed deep learning model was trained on 1538 patients and tested on an independent testing cohort of 549 patients. The overall sensitivity was 91.5% (195/213; p < 0.001, 95% CI: 89.2-93.9%), the overall specificity was 90.5% (304/336; p < 0.001, 95% CI: 88.0-92.9%) and the general AUC value was 0.955 (p < 0.001). Conclusions A deep learning model can accurately detect COVID-19 and serve as an important supplement to the COVID-19 reverse transcription-polymerase chain reaction (RT-PCR) test.
资助项目	Zhejiang Provincial Natural Science Foundation of China[LZY21F030001] ; National Natural Science Foundation of China[81870028] ; National Natural Science Foundation of China[81871370] ; Zhejiang provincial program for the Cultivation of High-level Innovative Health Talents[A-2017-CXCR02]
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000630283200008
资助机构	Zhejiang Provincial Natural Science Foundation of China ; National Natural Science Foundation of China ; Zhejiang provincial program for the Cultivation of High-level Innovative Health Talents
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/121440]
专题	中国科学院合肥物质科学研究院
通讯作者	Xu, Dong; Li, Ya-Qing
作者单位	1.Vanderbilt Univ, Med Ctr, Dept Biostat, Nashville, TN USA 2.Univ Chinese Acad Sci, Canc Hosp, Zhejiang Canc Hosp, 1 East Banshan Rd, Hangzhou, Zhejiang, Peoples R China 3.Chinese Acad Sci, Inst Basic Med & Canc IBMC, Hangzhou, Peoples R China 4.Huazhong Univ Sci & Technol, Tongji Hosp, Dept Resp & Crit Care Med, Tongji Med Coll, Wuhan, Peoples R China 5.Jianghan Univ, Huangpi Peoples Hosp, Dept Infect Med, Wuhan, Peoples R China 6.Zhejiang Prov Peoples Hosp, Dept Resp Med, Hangzhou, Peoples R China
推荐引用方式 GB/T 7714	Yao, Jin-Cao,Wang, Tao,Hou, Guang-Hua,et al. AI detection of mild COVID-19 pneumonia from chest CT scans[J]. EUROPEAN RADIOLOGY,2021.
APA	Yao, Jin-Cao.,Wang, Tao.,Hou, Guang-Hua.,Ou, Di.,Li, Wei.,...&Li, Ya-Qing.(2021).AI detection of mild COVID-19 pneumonia from chest CT scans.EUROPEAN RADIOLOGY.
MLA	Yao, Jin-Cao,et al."AI detection of mild COVID-19 pneumonia from chest CT scans".EUROPEAN RADIOLOGY (2021).