Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography

Corresponding authors: Kang Zhang, Jianxing He, Tianxin Lin, Weimin Li, Guangyu Wang

Affiliations: Faculty of Medicine, Macau University of Science and Technology, Macau, China; Department of Computer Science and Technology & BNRist, Tsinghua University, Beijing, China; Departments of Urology, Radiology, Emergency Medicine, and Respiratory Medicine, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China; Center for Translational Innovations and Department of Respiratory and Critical Care Medicine, West China Hospital, West China School of Medicine, Sichuan University, Chengdu, China; Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China; The First College of Clinical Medical Science, China Three Gorges University, Yichang, China; Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, China; Department of Radiology, Department of Infection Prevention and Control, Renmin Hospital, Wuhan University, Wuhan, China; Department of Thoracic Surgery/Oncology, the First Affiliated Hospital of Guangzhou Medical University, China State Key Laboratory and National Clinical Research Center for Respiratory Disease, Guangzhou, China; Department of Radiology, and Liver Disease Center, Sun Yat-Sen Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China; Guangzhou Kangrui AI Technology Co. and Guangzhou HuiBoRui Biological Pharmaceutical Technology Co., Ltd, Guangzhou, China; The First People’s Hospital of Yunnan Province, Kunmin, China; Department of Applied Biology and Chemical Technology, Hong Kong Polytechnic University, Hong Kong, China.

Publication date: this article was published on May 4, 2020

DOI: https://doi.org/10.1016/j.cell.2020.04.045

Highlights

Using a large computed tomography (CT) database from 3,777 patients, the researchers developed an AI system that can diagnose novel coronavirus pneumonia (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, the AI system identified important clinical markers that correlated with the NCP lesion properties. 

Nomination Reasons

Together with the clinical data, the AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. The authors have made this AI system available globally to assist the clinicians to combat COVID-19.

----------------------------------------------------------------------------------------------------------------------------------------------

This article has been nominated for Distinguished Research Awards, you can visit the website below and vote for the nominated publications:

https://www.molecularcloud.org/awards-for-distinguished-research.html.