Classification of COVID-19 CT images using transfer learning models

Abstract

Background and objective: SAARS-COV-2 is a respiratory illness caused by the novel Coronavirus (COVID-19) disease. The virus goes into the lungs through the respiratory tracks and damages the walls and linings of the air sacs in our lungs, as our body tries to fight it, our lungs become more inflamed and fill with fluid. This makes it harder to breathe. So, at early stages, deep learning applications can be used for screening and prediction at a rapid rate for diagnosing the lungs of patients. This paper uses Transfer learning methods. Four pretrained models were used in this study - VGG-16, VGG-19, Inceptionv3, Xception This paper addresses challenges while using pre-trained models in real-world. Also, high accuracies were achieved on these models.