Detection and screening of COVID-19 through chest computed tomography radiographs using deep neural networks.

December 2019 ended with a deadly virus outbreak named as COVID-19 or severe acute respiratory syndrome coronavirus 2 (SARS-COV-2). On January 30th, World Health Organization declared it as a “Public Emergency of International Concern,” which continuous its devastation all over the world. Currently 2,578,996 COVID-19 infections have been reported all over the world. China, Italy, United Kingdom, and United States of America are among the most affected areas by COVID-19. Italy suffered with 183,975 cases and 24,684 deaths so far. USA has 819,175 confirmed cases and 45,343 deaths whereas UK has 129,044 confirmed cases with 17,337 deaths. China had total infections of 82,788, and they were able to contain the virus. This showed a light that to contain the virus, there is a need of appropriate screening, isolation, and priority first aid treatment. These steps need to be taken to buy the time for the pharmaceutical to make the vaccine. A diagnosis of gold standard is nucleic acid testing and RT-PCR detection from viral RNA, which becomes quite challenging because of the laboratory testing quality and its availability. To combat this disease, there is a dire need of an alternative diagnostic method. Study of radio-graphic computed tomography images of COVID-19 gives the idea that deep learning methods can be implemented to extract specific features of COVID-19 aiding the clinical diagnosis. For this matter, a major part of data scientists and artificial intelligence (AI) researchers formed methods for screening of COVID-19 by AI means. These AI solutions related to the screening of COVID-19 will be discussed in this chapter. In addition, we propose a deep neural network which is trained on the X-ray images of the COVID-19 patients and normal X-ray images for the detection of COVID-19. Our method achieved validation accuracy of 0.95 which is quite promising accuracy for the classification of COVID-19 patients from the healthy ones.