Design and Implementation of COVID-19 Assistant Diagnostic System Based on Deep Learning
2021 International Conference on Culture-Oriented Science and Technology, ICCST 2021
; : 268-272, 2021.
Article
in English
| Scopus | ID: covidwho-1672715
ABSTRACT
In recent years, novel coronavirus pneumonia has spread rapidly around the world due to its strong infectiousness, and the medical systems of related countries are facing huge challenges. As the most intuitive and effective supplementary diagnostic basis for the results of nucleic acid tests, medical imaging screening has gradually become more and more important in epidemic prevention and control. In this context, this paper develops a novel coronavirus pneumonia-auxiliary diagnostic system by using deep learning techniques. This system can help medical staffs to diagnose the condition through X-Ray images quickly. This system builds a sample dataset by collecting lung X-ray images from two datasets and uses a neural network for auxiliary diagnosis training, which achieves an accuracy rate of 98%. Furthermore, two interactive visual interfaces in the form of PC-side applet and Web page are supported in the system, which makes it much easier for medical personnel to operate the system. © 2021 IEEE.
novel coronavirus pneumonia; ShuffleNet; X-ray images; Deep learning; Diagnosis; Disease control; Medical imaging; Nucleic acids; Websites; Condition; Coronaviruses; Design and implementations; Diagnostic systems; Learning techniques; Medical systems; Prevention and controls; ShuffleNets; X-ray image; Coronavirus
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
2021 International Conference on Culture-Oriented Science and Technology, ICCST 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS