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

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 d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jamal N. Hasoon, Ali Hussein Fadel, Rasha Subhi Hameed, Salama A. Mostafa, Bashar Ahmed Khalaf, Mazin Abed Mohammed, Jan Nedoma
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	COVID-19 diagnosis X-ray image Local binary pattern Haralick Machine learning K-nearest neighbor Physics QC1-999
Acceso en línea:	https://doaj.org/article/f1747ba132934ee08edcf5f42cf9d288
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f1747ba132934ee08edcf5f42cf9d288
record_format	dspace
spelling	oai:doaj.org-article:f1747ba132934ee08edcf5f42cf9d2882021-12-04T04:33:51ZCOVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images2211-379710.1016/j.rinp.2021.105045https://doaj.org/article/f1747ba132934ee08edcf5f42cf9d2882021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2211379721010342https://doaj.org/toc/2211-3797The 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.Jamal N. HasoonAli Hussein FadelRasha Subhi HameedSalama A. MostafaBashar Ahmed KhalafMazin Abed MohammedJan NedomaElsevierarticleCOVID-19 diagnosisX-ray imageLocal binary patternHaralickMachine learningK-nearest neighborPhysicsQC1-999ENResults in Physics, Vol 31, Iss , Pp 105045- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	COVID-19 diagnosis X-ray image Local binary pattern Haralick Machine learning K-nearest neighbor Physics QC1-999
spellingShingle	COVID-19 diagnosis X-ray image Local binary pattern Haralick Machine learning K-nearest neighbor Physics QC1-999 Jamal N. Hasoon Ali Hussein Fadel Rasha Subhi Hameed Salama A. Mostafa Bashar Ahmed Khalaf Mazin Abed Mohammed Jan Nedoma COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
description	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.
format	article
author	Jamal N. Hasoon Ali Hussein Fadel Rasha Subhi Hameed Salama A. Mostafa Bashar Ahmed Khalaf Mazin Abed Mohammed Jan Nedoma
author_facet	Jamal N. Hasoon Ali Hussein Fadel Rasha Subhi Hameed Salama A. Mostafa Bashar Ahmed Khalaf Mazin Abed Mohammed Jan Nedoma
author_sort	Jamal N. Hasoon
title	COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
title_short	COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
title_full	COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
title_fullStr	COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
title_full_unstemmed	COVID-19 anomaly detection and classification method based on supervised machine learning of chest X-ray images
title_sort	covid-19 anomaly detection and classification method based on supervised machine learning of chest x-ray images
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/f1747ba132934ee08edcf5f42cf9d288
work_keys_str_mv	AT jamalnhasoon covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT alihusseinfadel covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT rashasubhihameed covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT salamaamostafa covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT basharahmedkhalaf covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT mazinabedmohammed covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages AT jannedoma covid19anomalydetectionandclassificationmethodbasedonsupervisedmachinelearningofchestxrayimages
_version_	1718373006348124160

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

Ejemplares similares