Detecting COVID-19 in Chest CT Images Based on Several Pre-Trained Models

Abstract

<title>Abstract</title> COVID-19 virus (coronavirus) is causing a worldwide pandemic of severe respiratory illnesses (SARS-CoV-2). The unique virus was discovered in the Chinese city of Wuhan in December 2019 and has since spread throughout the world. For fear of spreading, the World Health Organization (WHO) issued a Public Health Emergency of International Concern. This paper attempted to offer an autonomous prediction of COVID-19 disease using chest CT scan images by using transfer learning techniques and deep learning algorithms. The dataset included 13413 samples divided into two categories: 7395 CT chest scan images of individuals with confirmed COVID-19 and 6018 images of suspicious cases. The Resnet (50) model has the best training results, Specificity, precision, Negative Predictive Value, False Positive Rate, False Discovery Rate, False Negative Rate, Accuracy, F1 Score, and Matthews Correlation Coefficient with values 0.9880, 0.9892, 0.9891, 0.9882, 0.0108, 0.0109, 0.0120, 0.9886, 0.9885, and 0.9772 respectively.