Diagnosis of Covid-19 Using X-Ray Images with the application of Deep Learning Techniques

The World Health Organization (WHO) proclaimed the coronavirus disease (COVID-19) is infectious disease, which has spread globally, it was declared as a pandemic on March 11, 2020. Fever, cough, sore throat, headache, malaise, muscle aches and shortness of breath were among the signs and symptoms of COVID-19. This virus affects the respiratory system of a person and creates white patchy shadows in the lungs X-ray image. Vaccines were introduced in early June 2021 for the public, but there is an urgent need for quick and accurate tools to improve healthcare system efficiency. The standard method for detecting COVID-19 is the Reverse transcription-polymerase chain reaction (RT-PCR) test. Therefore, it is necessary to implement an automatic detection system as a quick alternative diagnosis option to prevent COVID-19 spreading among people. Early detection of COVID 19 infection can save many lives in the prevailing situation. Deep Learning has advanced recently and has been useful in the classification of images, including those used in medical imaging. Convolutional Neural Networks (CNNs) have shown promising results in the detection of a variety of ailments, such as Parkinson's disease, malaria, and coronary artery disease. In order to identify diseases from datasets, pre-trained CNNs are frequently used. By applying filters in parallel to the images, the CNN model's parallelization technique recovers the features from the X-ray images. Detection of Corona virus using X-ray images is very convenient method and detection cost is also less compared to standard methods like RT-PCR. Neural networks were used to fully automate the analysis of COVID-19 chest radiographs. This method successfully classifying images into three categories: COVID-19, pneumonia, and normal (health), also improved the proposed method, the pre-processing component of the MLbased system. This method helps for detect people infected with the coronavirus faster and more accurately without human intervention, allowing doctors to make faster decisions.