A Method for Covid-19 Segmentation from X-Ray Images with U-Net

Abstract

The Covid-19 virus, which emerged in China and affected the whole world, resulted in the death of many people in a short time and caused many socio-economic problems. This virus, which is mostly seen in patients with chronic diseases, has been seen worldwide in cases where it progressed rapidly and resulted in death in healthy individuals. Early diagnosis is one of the most important things to be done for this virus, which has such great effects. It is necessary to minimize the risk by treating the patient after being diagnosed and isolated early. The long time elapsed while providing diagnosis in current diagnostic methods potentially increases the course of the virus. For this reason, it has been deemed necessary to investigate some alternative ways for the diagnosis of Covid-19. In this sense, a study area has been created because radiological images have the defining characteristics of the virus. In this study, Covid-19, pneumonia and normal classification was made using X-Ray images. Then, we tried to determine the area affected by the Covid-19 virus using the U-Net system for image tissue classification. It is aimed to provide early detection and reduce workload with deep learning techniques to be used to solve these problems.