A Deep Learning Approach to Detect COVID-19

DOI

10.2991/ahis.k.210913.032How to use a DOI?

Keywords

Convolutional Neural Network, Deep Learning, Computer Tomography, Machine Learning, Recurrent Neural Network

Abstract

Covid-19 is a viral disease that has been spreading rapidly infects both human beings and animals. The lifestyle of people, their physical and mental well-being and the economic condition of a country are distressingly disturbed due to the viral disease. Recently, vaccines have been prepared for COVID- 19 which have quite winning results. Yet we are unsure about the long-term effects of the vaccine. In a clinical study of COVID-19 infected patients shows that the covid patients are more likely to be infected from a lung infection after coming in contact with the virus. Chest x-ray (i.e., radiography) and chest computed tomography (CT) are a more effective imaging technique for diagnosing lung related problems. Yet, a significant chest x-ray is a lower cost process in comparison to chest CT. Adding to the previous statement, a chest X-ray helps to identify unusual and abnormal formations of a large variety of chest diseases such as pneumonia, cystic fibrosis, emphysema, cancer, etc. Deep learning is the most successful technique of machine learning, which provides useful analysis that can detect the COVID-19 virus and differentiate between a healthy lung and a virus infected lung successfully. Medical imaging, such as X-rays and CT scans, can aid in the early diagnosis of COVID-19 patients, allowing for more prompt therapy. For prediction, a Convolutional Neural Network (CNN) extracts information from chest x-ray pictures has been done. In order to classify an image as COVID or normal we need to have a segmented target so as to obtain this we use filters so that we can get the edge of the image. Keras Image Data Generator class is used to generate augmented images. Classification is performed with two classes: COVID-19 and Normal.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - C Shrada
AU  - Balakrishna Gudla
AU  - K Chaithra
AU  - T S Hassini
PY  - 2021
DA  - 2021/09/13
TI  - A Deep Learning Approach to Detect COVID-19
BT  - Proceedings of the 3rd International Conference on Integrated Intelligent Computing Communication & Security (ICIIC 2021)
PB  - Atlantis Press
SP  - 256
EP  - 261
SN  - 2589-4900
UR  - https://doi.org/10.2991/ahis.k.210913.032
DO  - 10.2991/ahis.k.210913.032
ID  - Shrada2021
ER  -