COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images

• Published in: Results in physics Vol. 31; p. 105045
• Main Authors: Hasoon, Jamal N., Fadel, Ali Hussein, Hameed, Rasha Subhi, Mostafa, Salama A., Khalaf, Bashar Ahmed, Mohammed, Mazin Abed, Nedoma, Jan
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021; The Author(s). Published by Elsevier B.V; Elsevier
• Subjects: COVID-19 diagnosis; Haralick; K-nearest neighbor; Local binary pattern; Machine learning; Support vector machine; X-ray image; COVID-19 diagnosis; Local binary pattern; Machine learning; K-nearest neighbor; X-ray image; Support vector machine; Haralick
• ISSN: 2211-3797; 2211-3797
• DOI: 10.1016/j.rinp.2021.105045

•We propose a method for early detection of COVID-19 through analysis of X-ray images.•The method performs preprocessing, RoI detection, segmentation, feature extraction, and classification steps.•The method contains six models, namely LBP-KNN, HOG-KNN, Haralick-KNN, LBP-SVM, HOG-SVM, and Haralick-SVM.•The six models are tested on 5,000 images using a 5-folds cross-validation approach.•The LBP-KNN model outperforms the other models and achieves an average accuracy of 98.66%, sensitivity of 97.76%, specificity of 100%, and precision of 100%. The term COVID-19 is an abbreviation of Coronavirus 2019, which is considered a global pandemic that threatens the lives of millions of people. Early detection of the disease offers ample opportunity of recovery and prevention of spreading. This paper proposes a method for classification and early detection of COVID-19 through image processing using X-ray images. A set of procedures are applied, including preprocessing (image noise removal, image thresholding, and morphological operation), Region of Interest (ROI) detection and segmentation, feature extraction, (Local binary pattern (LBP), Histogram of Gradient (HOG), and Haralick texture features) and classification (K-Nearest Neighbor (KNN) and Support Vector Machine (SVM)). The combinations of the feature extraction operators and classifiers results in six models, namely LBP-KNN, HOG-KNN, Haralick-KNN, LBP-SVM, HOG-SVM, and Haralick-SVM. The six models are tested based on test samples of 5,000 images with the percentage of training of 5-folds cross-validation. The evaluation results show high diagnosis accuracy from 89.2% up to 98.66%. The LBP-KNN model outperforms the other models in which it achieves an average accuracy of 98.66%, a sensitivity of 97.76%, specificity of 100%, and precision of 100%. The proposed method for early detection and classification of COVID-19 through image processing using X-ray images is proven to be usable in which it provides an end-to-end structure without the need for manual feature extraction and manual selection methods.