An Approach for COVID-19 Identification from Chest X-ray Images Using High-Resolution Networks

In this paper, we present an approach for COVID-19 identification from chest X-ray images by using high-resolution neural networks. These networks allow to connect high-to-low convolution streams in parallel. They can maintain high-resolution representations and generate different resolutions throughout the whole process. The high-resolution based models have shown the superior performance in several applications. The experiments were evaluated on a collection of three data sources containing 24,786 lung X-ray images, which were categorized into three classes including covid pneumonia, non-pneumonia, and viral pneumonia. The proposed approach can attain the overall accuracy of 98.2% and 97.56% for the training and testing set, respectively. The accuracy for each class is 99.37%, 94.83%, and 97.27%, respectively, for non-pneumonia, covid-pneumonia, and viral-pneumonia.