Cell, volume 181, issue 6, pages 1423-1433.e11
Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography
Kang Zhang
1
,
Xiao-hong Liu
2
,
Jun Shen
3
,
Ye Sang
4
,
Xingwang Wu
5
,
Yunfei Zha
6
,
Wenhua Liang
7
,
Chengdi Wang
8
,
Ke Wang
2
,
LinSen Ye
9
,
Ming Gao
3
,
Zhongguo Zhou
1
,
Liang Li
6
,
Jin Wang
9
,
Zehong Yang
3
,
Huimin Cai
10
,
Jie Xu
1
,
Lei Yang
10
,
WENJIA CAI
10
,
Wenqin Xu
1
,
Shaoxu Wu
3
,
Wei Zhang
3
,
SHANPING JIANG
3
,
Lianghong Zheng
11, 12
,
Xueyao Zhang
2
,
Li Wang
6
,
Lu Liu
11
,
Jiaming Li
11
,
Haiping Yin
13
,
Winston Wang
1
,
Oulan Li
10
,
Charlotte Zhang
10
,
Liang Liang
4
,
Tao Wu
4
,
Ruiyun Deng
12, 14
,
Kang Wei
1
,
Yong Zhou
1
,
陈挺 Ting Chen
2
,
Johnson Yiu Nam Lau
15
,
Manson Fok
1
,
Jianxing He
7
,
Tianxin Lin
3
,
Weimin Li
8
,
Guang-Yu Wang
2
10
Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China.
|
11
Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China
|
12
Guangzhou Kangrui AI Technology Co. and Guangzhou HuiBoRui Biological Pharmaceutical Technology Co., Ltd, Guangzhou, China.
|
13
The First People's Hospital of Yunnan Province, Kunmin, China.
|
Publication type: Journal Article
Publication date: 2020-06-01
General Biochemistry, Genetics and Molecular Biology
Abstract
Summary
Many COVID-19 patients infected by SARS-CoV-2 virus develop pneumonia (called novel coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid diagnosis and identification of high-risk patients for early intervention are challenging. Using a large computed tomography (CT) database from 3,777 patients, we developed an AI system that can diagnose NCP and differentiate it from other common pneumonia and normal controls. The AI system can assist radiologists and physicians in performing a quick diagnosis especially when the health system is overloaded. Significantly, our AI system identified important clinical markers that correlated with the NCP lesion properties. Together with the clinical data, our AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. We have made this AI system available globally to assist the clinicians to combat COVID-19.
Are you a researcher?
Create a profile to get free access to personal recommendations for colleagues and new articles.