Your browser doesn't support javascript.
Survey of Studies of COVID-19 Diagnosis Based on Deep Learning
Jisuanji Gongcheng/Computer Engineering ; 47(5):1-15, 2021.
Article in Chinese | Scopus | ID: covidwho-1924846
ABSTRACT
The Corona Virus Disease 2019 COVID-19 is highly infectious and pathogenic, posing a serious threat to public safety.  Rapid and accurate detection and diagnosis of COVID-19 is key to the epidemic control. The existing detection and diagnosis methods are mainly based on nucleic acid tests or manual diagnosis using medical images.  However, nucleic acid tests are time-consuming and require special test boxes, while the manual diagnosis relies heavily on professional knowledge, takes longer time for analysis and often fail to detect concealed lesions. Since then, with the development of X-ray and Computer Tomography CT image datasets, researchers have built many deep learning-based COVID-19 detection and diagnosis models which effectively assist medical experts in the efficient diagnosis and treatment of COVID-19. This paper lists the mainstream image datasets for the detection and diagnosis of COVID-19 and related evaluation metrics. Then, it introduces the existing deep learning-based models for COVID-19 diagnosis from the perspectives of the model task and the image data type, and on this basis compares and analyzes the detection performance of the models in six different dimensions Backbone network, data sets, image types, model performance, classification task types and park opening situation. In addition, this paper introduces the excellent application systems used to fight against COVID-19, and discusses the development trend of the studies in this field. © 2021, Editorial Office of Computer Engineering. All rights reserved.
Keywords

Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Observational study Language: Chinese Journal: Computer Engineering Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Observational study Language: Chinese Journal: Computer Engineering Year: 2021 Document Type: Article