Development and evaluation of an artificial intelligence system for COVID-19 diagnosis

• Published in: Nature communications Vol. 11; no. 1; p. 5088
• Main Authors: Jin, Cheng, Chen, Weixiang, Cao, Yukun, Xu, Zhanwei, Tan, Zimeng, Zhang, Xin, Deng, Lei, Zheng, Chuansheng, Zhou, Jie, Shi, Heshui, Feng, Jianjiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 09.10.2020; Nature Portfolio
• Subjects: 631/114/1305; 692/699/255/1578; 692/700/139; 692/700/1421/2025; Adult; Aged; Aged, 80 and over; Artificial Intelligence; Betacoronavirus; Coronavirus Infections - diagnostic imaging; COVID-19; Deep Learning; Diagnosis, Differential; Female; Humanities and Social Sciences; Humans; Male; Middle Aged; multidisciplinary; Pandemics; Pneumonia - diagnostic imaging; Pneumonia, Viral - diagnostic imaging; ROC Curve; SARS-CoV-2; Science; Science (multidisciplinary); Tomography, X-Ray Computed; Young Adult
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-020-18685-1

Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 . In some contexts, rapid detection of COVID-19 from CT scans can be crucial for optimal patient management. Here, the authors present a Deep Learning system for this task with multi-center data, human reader comparison and age stratified results.