Deep Learning Approach to Recognize COVID-19, SARS and Streptococcus Diseases from Chest X-ray Images

Abstract

Corona virus disease (COVID-19) became pandemic for the world in the year 2020 and large numbers of people are infected worldwide due to the rapid widespread of this infectious virus. Pathological laboratory testing of a large number of suspects becomes challenging and producing false-negative results. Therefore, this paper aims to develop a deep learning basedapproach for automatic detection of COVID-19 infection using medical X-ray images. The proposed approach is used for the fast detection of COVID-19 along with other similar diseases such as Streptococcus, and severe acute respiratory syndrome (SARS) positive cases. A 2D-convolution neural network (2D-CNN) is used to recognize the graphical features of X-ray image’s dataset of COVID-19 positive, Streptococcus and SARSpatients. The proposed approach is tested on the COVID-chest X-Ray dataset. Experiments produced individual accuraciesof COVID-19, Streptococcus, SARS disease and normal persons are 100%, 90.9%, 91.3%, and 94.7% respectively and achieved an overall accuracy of 95.73%. From the experimental results, it is proved that the performance of the proposed approach is better as compared to the mentioned state-of-art methods.