ABSTRACT
Coronavirus or COVID-19 is an infectious disease that has been identified in humans. The symptoms range from mild to extremely severe when a person infected with COVID-19 may suffer from pneumonia. Chest imaging that may include radiography, computed tomography (CT), and ultra-sound can be used for detecting thepresence of the virus. The certain distinctive factors that help differentiate COVID-19 from pneumonia are that COVID-19 affects both lungs as opposed to one and lungs may show a ground-glass appearance and abnormalities in liver et cetera. A drawback anyway about this method is that it requires an expert radiologist and provided the size of this pandemic, and the number of cases greatly outnumbers the radiologists. This paper aims to establish a proposal to a reliable, fully automated diagnosis powered by deep learning for diagnosis of COVID-19 from CT. The approach is divided into three phases. The first phase is to look out for abnormalities in lungs. The second phase is to determine the presence of pneumonia using OpenCV for pointingout the regions of interest. The third is to distinguish COVID-19 from pneumonia proceeding on the guidelines mentioned above, which are both the lungs affected as opposed to one, and using the regions that were obtained using OpenCV, endorsing the potential presence of COVID-19. The model, based on convolutional networks, takes advantage of TensorFlow 2.1 and Keras deep learning libraries since both were later integrated and can be used conjointly for the identification and the OpenCV library for image loading and preprocessing. Tenfold method is used for the division of training and test set, and the evaluation metric is accuracy. The model was trained against a dataset of a thousand images (owing to the lack of x-ray images of patients affected with coronavirus), with images of normal versus abnormal lungs in a ratio of 1:1, and was tested for accuracy using the confusion matrix. It provided an accuracyof 86% in pointing out the abnormalities in lungs. Then, the identification of images with normal pneumonia versus those infected with coronavirus was done with an accuracy of 75%. © 2022 Scrivener Publishing LLC.