Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 using a Deep CNN and ResNet 50

Thumbnail Image

Files

document.pdf (540.36 KB)

Links to Files

https://ijisae.org/index.php/IJISAE/article/view/2499

Permanent Link

http://hdl.handle.net/11603/26898

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Student Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0001-6445-5141

Date

2023-01-14

Type of Work

journal articles
Text

Department

Program

Citation of Original Publication

Shivadekar, Samit, Bhavesh Kataria, Sheela Hundekari, Kirti Wanjale, Vijaya P. Balpande, and Renuka Suryawanshi. 2023. “Deep Learning Based Image Classification of Lungs Radiography for Detecting COVID-19 Using a Deep CNN and ResNet 50”. International Journal of Intelligent Systems and Applications in Engineering 11 (1s):241-50. https://ijisae.org/index.php/IJISAE/article/view/2499.

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)

Subjects

Abstract

The lungs radiography (chest x-ray) is a screening tool for COVID-19 that is widely used; however, its interpretation can be difficult due to the presence of subtle changes in the lungs caused by the virus, which can be seen in the images. This is the case even though the lungs radiography is widely used. In this article, we present a CNN model that can be utilized for the classification of data derived from lungs radiography. The proposed model was tested and refined using a series of lungs radiography taken from patients diagnosed with COVID-19. When it came to the classification of the data, the findings of the research showed that the CNN model performed significantly better than the conventional approaches did. The accurateness of the anticipated model was found to be 96.2% while its sensitivity was found to be 96.8%. It was demonstrated that it had the potential to be utilized for the purpose of classifying the data associated with the presence of COVID-19. In addition, radiologists can use it to help them interpret the lungs radiography that have been taken.