Performance Comparison for COVID-19 Chest X-ray Images Classification based on Different CNNs

Abstract

Nowadays, the detection of the disease that is called Coronavirus or COVID-19 is essential for the whole world. Scientific researchers have spent significant efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose and treat COVID-19. Convolutional neural networks (CNNs), have obtained remarkable results in numerous applications. One of these applications is image classification. Chest radiograph (X-ray) images can be requested for early COVID-19 classification of patients. Hence, this paper makes demonstrates different CNN architectures utilizing Chest radiograph database images for COVID-19: detection ( Kaggle’s X-ray chest images). It contains three different classes of images: 1) COVID-19, 2) normal, and 3) viral pneumonia Chest radiograph images. Therefore, three alternative CNN architectures like SqueezeNet, GoogleNet, and ResNet 50 have been realized using Matlab 2019a and numerical simulation has been performed. GoogleNet has achieved good performance based on the accuracy obtained with a value of 97.02% and it saves time-consuming. A performance comparison between different techniques has been carried out and this comparison shows that the detection is accurate enough for the non-uniform structure of the chest radiograph images.