Automated Detection of COVID-19 in Chest CT Scans Using Transfer Learning with Ensemble Models

The COVID-19 virus causes serious harm to both human and animal health. This illness, which has infected millions of people and is now being referred to as a pandemic worldwide, has spread to many people. Numerous rapid tests are performed on suspects, and it is getting harder to stop the virus from spreading. Recently, a number of methods depending on trying to learn have been created to automate the detection symptoms of COVID-19 disease computed exam with a Chest Tomography (CT) scanner pictures. The majority of the publications, however, depend only on a statistical forecast, therefore the results either be or not be trustworthy. In this paper, we employ a variety of transfer of learning models with an ensemble approach, which produces better outcomes than the current ensemble approach with accuracy and precision both of 99.5 %, recall 99.504 %, and F1-score 99.497 %, respectively, and detects the COVID-19 virus from the lung disorders that are both common and serious.