Deep learning framework for classification of COVID-19 from Chest X-rays

Abstract

The Coronavirus Disease 2019 (COVID-19) has emerged as the most pressing health concern in recent years. In addition, a wide variety of severe acute respiratory syndrome-related COVID-19 strains are now in the process of developing (SARS). Therefore, the identification of all of these variations utilising a Real-time polymerase chain reaction (RT-PCR) test is a challenging endeavour that takes a significant amount of time. Due of the intricate structure of the chest x-ray (CXR) picture, traditional approaches were unable to correctly categorise the COVID-19 at an early stage. As a result, the primary emphasis of this paper is placed on the use of an artificial intelligence strategy that is based on deep learning convolutional neural networks (DLCNN) for the classification of COVID-19 illness. In the beginning, the hybrid features are extracted from the CXR dataset by using stacked auto ensemble (SAE), a technique that retrieved features by partitioning data into various subsets. This approach was used. After that, a DLCNN model is trained with these characteristics in order to classify COVID-19 for each test CXR picture. According to the findings of the simulations, the suggested classification led to superior results in terms of both subjectivity and objectivity in comparison to both traditional machine learning and deep learning approaches.