Deep Learning-based CAD System for Predicting the COVID-19 X-ray Images

Abstract

Abstract According to World Health Organization data, Coronavirus (COVID-19) has infected about 660, 378, 145 patients around the world. It is nonetheless difficult for physicians to detect COVID-19 infections out of CT or X-ray radiographs. Thus, several computer-aided diagnosis (CAD) systems based on deep learning and radiographs were developed to detect COVID-19 infections. However, the majority of approaches considered small datasets, which is ineligible to provide diverse COVID-19 radiographs. This work utilizes a massive number of X-ray radiographs, and compared standard CNN, DenseNet-121, and GoogLeNet for isolating COVID-19 infections out from normal and other pneumonia radiographs. The dataset in this work is large enough to evaluate the realistic performance of those models in labeling COVID-19 infections. Considering the time complexity, accuracy, precision, recall, and F1 score, the experimental results shows that the DenseNet-121 is not only the optimal model, but also there is superior for standard CNN compared to the second output of GoogLeNet, which is an unexplained phenomenon.