Detection of COVID-19 from CT Images Using resnet50

Abstract

Coronavirus (COVID-19) outbreak which is a global health pandemic occurred due to (SARS) Severe Acute Respiratory Syndrome and SARs-CoV-2 has an immeasurable impact on the entire world. In this century, COVID-19 is the third viral contagious disease caused due to SARS-CoV-2 along with Severe Acute Respiratory Syndrome-1(SARS-CoV-1) and Middle East Respiratory Syndrome (MERS). Affecting almost every country of every continent COVID-19 has killed more than 300,000 people. To identify, the severity of the disease CT findings are useful along with the RT-PCR test. In this study, CT images are pre-trained and fine-tuned further trained and tested using the ResNet50 model. This model can be used to classify COVID-19 cases from pneumonia and other medical conditions. By using this model, early detection and the low fatality rate can be achieved.

Note: Funding: None to declare

Declaration of Interest: None to declare

Keywords: COVID-19, CT images, Deep Learning

JEL Classification: C00, L15