Covid-19 Identification Using Deep Neural Networks

COVID-19 is a novel virus which is originated from Wuhan, a city in China. By March 2021, World Health Organization has confirmed the virus has increased in the number of infections to over 117 million cases globally. In this scenario of increasing Corona infected patients, most hospitals are lagging in the availability of the Corona test kits. Owing to the lack of precise automated toolkits, auxiliary diagnostic tools are in high demand. Therefore, it becomes necessary to enforce AI-based automatic detection techniques. It can also address the issue of unavailability of physicians in remote areas. This study proposes the use of deep neural networks and transfer learning for the detection of COVID-19 infectees through radio-graphs of chest X-rays. We have used hand-crafted Convolutional Neural Network (CNN) besides using the existing famous pre-trained networks employing transfer learning. Remarkable accuracy achieved was 96.89% for our hand-crafted CNN, 92.67% for ResNet34, and 98.26% on DenseNet-121, respectively. However, our hand-crafted CNN required 8 million less parameters than ResNet34 and comparable to DenseNet-121.