CoroNet: A Deep Neural Network for Detection and Diagnosis of Covid-19 from Chest X-ray Images

The novel Coronavirus also called Covid-19 originated in Wuhan, China in December 2019 and has now spread across the world. It has so far infected around 1.5 million people and claimed approximately 88000 deaths overall. As the number of cases are rapidly increasing, most of the countries are facing shortage of testing kits. The limited quantity of testing kits and increasing number of daily cases encouraged us to come up with an alternate approach that can aid radiologists and clinicians in detecting Covid-19 directly from the chest X-rays. Therefore, in this study, we propose CoroNet, a deep convolutional neural network approach to automatically detect Covid-19 infection from chest X-ray images. The deep model called CoroNet has been trained and tested on a dataset prepared by collecting Covid-19 and other chest pneumonia X-ray images from two different publically available databases. With an accuracy and F-measure of 96% and 93.2%, the proposed technique can be very beneficial for health experts to understand the critical aspects associated with COVID-19 cases. The results can further improve as more data becomes available. However, till then it can still be a helping tool to aid clinicians and radiologists to triage the patients. The tool can also be helpful in keeping track of the progress of disease in positive cases