Many methods have been presented to detect COVID-19. Computer vision methods have been widely preferred to detect COVID-19 by using chest X-ray and computed tomography (CT) images. Quick clinical findings can monitor and prevent the spread of pandemic diseases such as COVID-19, and allow doctors to better handle patients while dealing with a high workload. While the standard routine diagnostic method is a laboratory test, it is time-consuming, costly, and requires a well-equipped laboratory for research. Until now, CT has become a quick method of diagnosing COVID-19 patients. The performance of radiologists in COVID-19 diagnosis is modest, though. Consequently, further studies are required to enhance the efficiency of COVID-19 diagnosis. This chapter presents an automated COVID-19 detection model using using CT images. The main goal of the proposed framework is to achieve high classification accuracy, using transfer learning and convolutional neural networks (CNN). Different widely-known CNNs, such as AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xceptionn were used to classify an infection of COVID-19.