Abstract
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.
Highlights
Detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease
We developed and evaluated a deep learning-based COVID-19 diagnosis system, using multi-class multicenter data, which included 11,356 CT scans from 9025 subjects consisting of COVID-19, community acquired pneumonia (CAP), influenza, and non-pneumonia
Three reader study cohorts were randomly chosen from test cohort with respectively 100, 100, and 50 subjects for three tasks, differentiating pneumonia from healthy, differentiating COVID-19 from CAP, and differentiating COVID-19 from influenza
Summary
Detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. 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. Comparing to other lung diseases, such as lung nodule detection[18,19,20], tuberculosis diagnosis[16,21], and lung cancer screening[15], differentiating COVID-19 from other pneumonias has unique difficulty, i.e., high similarity of pneumonias of different types (especially in early stage) and large variations in different stages of the same type. The AI diagnosis algorithm has the advantages of high efficiency, high repeatability, and easy large-scale deployment
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
