Automatic detection of COVID-19 and pneumonia from chest X-ray images using texture features.

COVID-19 has been a devastating pandemic, causing serious and sometimes irreparable damages to body organs. The sooner the existence of this virus in the body is recognized, the more effective the treatments are. This early detection can break the transmission chain faster, reducing the burden of this disease on the society. Since there exist issues regarding the reliability of RT-PCR tests to diagnose COVID-19, examining chest radiographs, especially chest X-ray images, are recommended as well. In this paper, we propose a machine learning algorithm to automatically classify patients in the target groups of COVID-19, pneumonia, and normal, based on chest X-ray images. Our algorithm generates two complementary images from each raw image in the dataset, and only works on a 4-feature vector extracted from the gray level co-occurrence matrix of each image for the classification, based on the k-nearest neighbors algorithm. It can work robustly in the presence of limited data. The speed, simplicity, and the independence from large computational resources are of other advantages of the proposed algorithm. Despite the simplicity and speed, as the results show, the algorithm can compete tightly with the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]