Detection of Covid-19 in chest X-ray images using a Resnet-50
No Thumbnail Available
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
University of Oum El Bouaghi
Abstract
Covid-19 is a serious illness that has affected millions of individuals worldwide, it has been declared as a pandemic by the World Health rganization (WHO) on 11th March 2020. One critical element in combating COVID-19 is the capacity to identify infected individuals early and place them under special care. Chest computed tomography (CT) and chest X-ray are two medical imaging methods widely used to identify lung infection. This study presents a deep convolutional neural network (DCNN) based on a pre-trained deep CNN model Residual Network (Resnet-50) that can distinguish COVID-19 from two other classes (normal and pneumonia) by using 4-fold cross validation. The dataset used consists of 317 frontal x-ray images of COVID-19, 5836 pneumonia, and 1203 normal chest x‐ray images. The experimental results demonstrate that the proposed model is effective at identifying COVID-19 from normal and pneumonia cases, with average accuracy, precision, and sensitivity cases of 97.3 %, 98.1 %, and 95.1%, respectively
Description
Keywords
COVID-19; Chest X-ray images; Classification; Deep-learning; Pre-trained deep CNN model