Open AccessAutomatic Classification of Covid-19 Chest X-Ray Images Using Local Binary Pattern and Binary Particle Swarm Optimization for Feature Selection
Author(s) -
Bazhdar N. Mohammed,
Firas Husham Almukhtar,
Raghad Zuhair Yousif,
Yazen S. Almashhadani
Publication year - 2021
Publication title -
cihan university-erbil scientific journal
Language(s) - English
Resource type - Journals
eISSN - 2707-6377
pISSN - 2519-6979
DOI - 10.24086/cuesj.v5n2y2021.pp46-51
Subject(s) - local binary patterns , pattern recognition (psychology) , artificial intelligence , feature selection , support vector machine , computer science , feature extraction , histogram , computer aided diagnosis , particle swarm optimization , robustness (evolution) , image (mathematics) , machine learning , biology , biochemistry , gene
Novel Coronavirus disease 2019 (COVID-19) is a type of pandemic viruses that cause respiratory tract infection in humans. The clinical imaging of Chest X-Ray (CXR) by Computer Aided Diagnosis (CAD) plays an important role to identify the patients who infected by COVID-19. The objective of this paper presents a Computer Aided Diagnosis (CAD) method for automatically classify 110 frontal CXR images of contagious people according to Normal and COVID-19 infection. The proposed method contains of four phases: image enhancement, feature extraction, feature selection and classification. Gaussian filter is performed to de-noise the images and Adaptive Histogram Equalization (AHE) for image enhancement in pre-processing step for better decision-making process. Local Binary Pattern (LBP) features set are extracted from the dataset. Binary Particle Swarm Optimization (BPSO) is considered to select the clinically relevant features and developing the robust model. The successive features are fed to Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. The experimental results show that the system robustness in classification COVID-19 from Normal images with average accuracy 94.6%, sensitivity 96.2% and specificity 93%.