Detection of Covid-19 and Pneumonia from Colorized X-Ray Images by Deep Learning

Abstract

The Coronavirus, which was first seen in Wuhan, China in December 2019, turned into an epidemic in a very short time. This virus, which has very serious effects especially in people with chronic diseases, causes global problems. The early diagnosis of Covid-19 and the isolation of the infected patient and then the treatment is very important. The inadequacy of diagnostic kits and the fact that radiological images contain the defining features of the virus have created a great field of study in this field. In addition to these, estimating the measures to be taken due to the increase in the number of cases is also important in terms of planning the processes related to many affected areas, especially the health field. Some models are used to take all these measures. In addition to these statistical models, deep learning-based artificial intelligence studies are also being developed. Particularly, the density in the field of health and the heavy workload of the employees have increased the tendency to develop artificial intelligence-based systems. In this context, the presence of unique symptoms related to Covid-19 in X-Ray images, which are frequently used in the diagnosis of many diseases in the field of health, has enabled the classification of these images with deep learning methods. Especially since Covid-19 and Pneumonia disease have similar patterns, it is necessary to classify these diseases by finding the uniqueness that even the human eye cannot see in the classification of these diseases. In this study, it is aimed to provide higher accuracy by colorizing X-ray images with deep learning methods and obtaining clearer images thanks to pre-trained networks. With this determination, the disease was classified as Covid-19/Pneumonia/Normal. In the study, the accuracy was provided with 98.78%.