Affiliation:
1. University of Leicester, Leicester, UK
2. Fourth People's Hospital of Huai'an, Huai'an, Jiangsu Province, China
Abstract
(
Aim
) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. (
Methods
) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom
deep stacked sparse autoencoder (DSSAE)
model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. (
Results
) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). (
Conclusion
) Our method outperforms 10 state-of-the-art approaches.
Funder
Royal Society International Exchanges Cost Share Award, UK
Medical Research Council Confidence in Concept Award, UK
Hope Foundation for Cancer Research, UK
Publisher
Association for Computing Machinery (ACM)
Subject
General Computer Science,Management Information Systems
Reference39 articles.
1. Does living in previously exposed malaria or warm areas is associated with a lower risk of severe COVID-19 infection in Italy?;Carta M. G.;Biointerface Research in Applied Chemistry,2021
2. Risk factors for mortality in hospitalized patients with COVID-19 at the start of the pandemic in Belgium: a retrospective cohort study
3. Pfizer and BioNTech say their COVID-19 vaccine is successful in late-stage trial
4. SARS-CoV-2 RNA detection in the air and on surfaces in the COVID-19 ward of a hospital in Milan, Italy
5. Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases;Ai Tao;Radiology,2020
Cited by
23 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献