Detection of Covid 19 from the Lungs X-ray Images by Using the Deep Learning Techniques

Abstract

The corona epidemic spreads frighteningly and rapidly in all countries of the world, forcing humanity to an abnormal life. Failure to fully control the epidemic and to find adequate and effective vaccines endangers human life. Fighting against the epidemic becomes important, as all these measures could not be taken in the near future. For this reason, it is important to detect whether the person caught the virus expressed in thousands of people is covid or not and to take the necessary measures. For this purpose, an artificial intelligence-based study has been proposed that will speed up the diagnosis of the pandemic by saving labor and expense. In the study, X-Ray images were processed with the most up-to-date deep image processing techniques, and an objective decision support system was created, independent of the doctor's expertise. The proposed system can classify x-ray images as Normal, Covid -19 and Viral Pneumonia using pre-trained deep learning networks (AlexNet, GoogleNet, ResNet8 and ResNet50). The overall accuracies of the networks (AlexNet, GoogleNet, ResNet8 and ResNet50) were 95.7%, 94.5%, 95.4%, 97.4% respectively. It is easy to diagnose in the advanced stages of the disease. As with most diseases, early diagnosis is important in covid-19. With the proposed system based on deep learning, an especially useful tool has been created in combating the pandemic by determining the disease at an early stage. The proposed system can also be used in areas with shortage of health personnel such as rural and remote areas.