Mohammadreza Behnia - Department of Computer Engineering and Information Technology, International Azad University Iran
Touba Torabipour - Department of Computer Engineering and Information Technology, Payame Noor University (PNU), Tehran, Iran
Safieh Siadat - Department of Computer Engineering and Information Technology, Payame Noor University (PNU), Tehran, Iran

Lung infection is the most dangerous sign of Covid ۱۹. X-ray images are the most effective means of diagnosing this virus. In order to detect this disease, deep learning algorithms and machine vision are widely used by computer scientists. Convolutional neural networks (CNN), DenseNet۱۲۱, Resnet۵۰, and VGG۱۶ were used in this study for the detection of Covid-۱۹ in X-ray images. In the current study, ۱۳۴۱ chest radiographs from the COVID-۱۹ dataset were used to detect COVID-۱۹ including infected and Healthy classes using a modified pre-trained CNN (train and test accuracy of ۹۹.۷۵% and ۹۹.۶۳%, respectively). The DENSENET۱۲۱ model has a training accuracy of ۴۳.۸۹% and a test accuracy of ۵۷.۸۹%, respectively. The train and test accuracy of ResNet-۵۰ are, respectively, ۸۹.۴۳% and ۹۰%. Additionally, the CNN model has test and train accuracy of ۹۸.۱۳% and ۹۶.۷۳%, respectively. The suggested model has COVID-۱۹ detection accuracy that is at least ۱% higher than all other models.

convolutional neural network, Deep Learning, Chest X-Ray, COVID-۱۹