ABSTRACT
COVID-19 which is a subclass of severe acute respiratory syndrome (SARS) is a viral disease which emerged from China in 2019. At first, there are shorthand of test kits available to diagnose the COVID-19 disease. The tests available to diagnose the COVID-19 are RT-PCR (real-time polymerase chain reaction), Rapid Antigen test and Antibody test. But in these, only RT-PCR has the high accuracy, and it is a time-taking process. It takes nearly from 4 to 48 h. Here, AI plays an important role in diagnosing the disease. In the recent years, AI becomes a part of medical field and is widely used in classification. The chest X-Rays are used to detect the COVID-19 using deep learning and the model used to detect the COVID-19 is ResNet18 which is a residual network containing 18 layers. In this work, we classified four types of classes to make sure that our model performance is better and classify accurately. The data set contain a total of 5365 images. In this, we used 80% of data for the training and 20% for validation. The accuracy obtained in classification of three classes is 96.67% and for four classes, the accuracy is 91%. We have also used another model for comparison which ResNet50 and achieved an accuracy of 75%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.