CAVDL:A Comparative Analysis of Diverse DL Models for Enhancing COVID-19 Images

The global health crisis has brought to light the critical role that medical imaging, particularly X-rays, play in the diagnosis and surveillance of COVID-19 infections. The capacity to increase X-ray picture quality and diagnostic accuracy has greatly improved with the development of sophisticated...

Full description

Saved in:
Bibliographic Details
Published in2024 Parul International Conference on Engineering and Technology (PICET) pp. 1 - 6
Main Authors Jain, Arti, Kaliyar, Rohit Kumar, Sharma, Shallu
Format Conference Proceeding
LanguageEnglish
Published IEEE 03.05.2024
Subjects
Biomedical imaging
Classification
COVID-19
Deep Learning(DL)
Image enhancement
Indexes
Measurement
PSNR
Robustness
SSIM
Surveillance
Visualization
X-rays
Online AccessGet full text

Cover

More Information
Summary:The global health crisis has brought to light the critical role that medical imaging, particularly X-rays, play in the diagnosis and surveillance of COVID-19 infections. The capacity to increase X-ray picture quality and diagnostic accuracy has greatly improved with the development of sophisticated image enhancing methods. The objective of this research is to assess and compare the efficacy of several image enhancement models in improving the visual quality, feature preservation, and diagnostic usefulness of COVID-19 X-ray pictures. To give a comprehensive understanding of each model's limitations and robustness, we use a strict evaluation process that includes both quantitative indicators and qualitative assessments. We employed a variety of evaluation criteria, such as PSNR (peak signal-to-noise ratio) and structural similarity index metrics (SSIM), to do the comparison. In this study, using a carefully chosen COVID-19 X-ray dataset, we thoroughly compared different state-of-the-art models with existing classification models.
DOI:10.1109/PICET60765.2024.10716166