COVID Detection Using Chest X-Ray and Transfer Learning
As per World Health Organization, COVID-19 is causing even the most important health systems across the countries under considerable strain. The advanced recognition of COVID 19 will result into decreasing the stress of a lot of health systems. Much similar to the customary usage of Chest X-Rays for...
| Main Authors: | Jain, S., Sindhwani, N., Anand, R., Kannan, R. |
|---|---|
| Format: | Article |
| Institution: | Universiti Teknologi Petronas |
| Record Id / ISBN-0: | utp-eprints.33271 / |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Online Access: |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127672464&doi=10.1007%2f978-3-030-96308-8_87&partnerID=40&md5=00f52e3cc1bf92f1756740b882e2905e http://eprints.utp.edu.my/33271/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: |
As per World Health Organization, COVID-19 is causing even the most important health systems across the countries under considerable strain. The advanced recognition of COVID 19 will result into decreasing the stress of a lot of health systems. Much similar to the customary usage of Chest X-Rays for detecting different pathologies, COVID-19 can also be detected using X-Ray of patients that indicates a very critical function in the diagnosis of SARS Covid-19. With rampant growth in the area of Deep Learning (DL) as well as Machine Learning (ML), it is much easier to design the framework that can detect COVID-19 infection easily. This paper proposes deep learning-based detection process by incorporating the concept of Transfer Learning for the classification of this pandemic using X-ray images of chest. This non-invasive and early-prediction of the corona virus by observing the X-rays of chest can subsequently be utilized to estimate the expansion of COVID-19 in the patients. This study got a maximum of 97 classifiers� accuracy using ResNet based model. This method can be utilized to upscale the effectiveness of the screening process. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. |
|---|