Detection of COVID-19 from Chest Radiographs: Comparison of Four End-to-End Trained Deep Learning Models

Abstract

The coronavirus disease (COVID-19), which has been declared as a pandemic by the World Health Organization (WHO), is an infectious disease killing more than 660,000 people worldwide. During this challenge, Deep learning, a subset of artificial intelligence, could be used as an effective tool for assisting radiologists in detecting COVID-19 cases, as well as reducing the burden on healthcare systems. Correct detection of COVID-19 cases using X-ray images could help quarantine high-risk patients until a thorough examination is followed. In this study, we aim to compare four state-of-the-art deep learning models (VGG-16, VGG-19, EfficientNetB0, and ResNet50) using 464 chest X-ray images of COVID-19 and normal cases. A classification head is added to all these models in order to achieve the best performance. The VGG-19 model achieved the best performance in terms of AUROC among all the tested models with a value of 0.91. Also, the heatmaps of X-ray images are provided, which could be used to specify the disease's area within the lung.