Hybrid feature extraction technique for automatic classification of COVID-19 chest CT images

ABSTRACTCOVID-19 has seriously affected normal life as well as public safety. It is extremely transmissible and has now infected millions of people worldwide. To obtain more image features of the lungs, Computed Tomography (CT) scans are widely used. However, manual examination of CT images for abnormal areas of COVID-19 disease can be time-consuming, and it is highly subjective to determine whether they are infected. To rapidly screen patients, Machine Learning (ML) can be used to determine whether patients have the disease. In this paper, a hybrid extraction technique is used to extract feature vectors from CT images, which is a mixture of a histogram of orientation gradients (HOG) extraction technique and a local binary pattern (LBP) extraction technique. In this experiment, 960 NON-COVID-19 and 960 COVID-19 were adopted to train the model, and 240 NON-COVID-19 and 240 COVID-19 were used to test the model. And the CT images were scaled to a uniform size. After obtaining the feature vectors using HOG and LBP feature extraction methods, The CT images were classified using a Support Vector Machine (SVM) classifier optimised by Particle Swarm Optimisation (PSO). In the performance evaluation of the presented classification model, the combination of the HOG feature extraction technique and the LBP feature extraction technique resulted in a substantial improvement in the classification effectiveness of the SVM. HOG_LBP PSO SVM improved Accuracy to 97.5%, Precision to 97.75%, Recall to 97.27%, Specificity to 97.25%, F1_score to 97.50%, and Mcc to 95.01%.KEYWORDS: COVID-19HOGLBPHOG_LBP SVM AcknowledgementsThis work was supported by the National Natural Science Foundation of China (No. 31800836), China Postdoctoral Science Foundation (No. 2020M682285), Medical and Health Research Project in Luoyang (No. 2001027A), and Construction Project of Improving Medical Service Capacity of Provincial Medical Institutions in Henan Province (No. 2017-51). Project of Luoyang Science and Technology Bureau (2020YZ23).We acknowledge the support of these foundations. We would like to thank the Soares research group for providing the public available SARS-CoV-2 CT scan dataset [20].Disclosure statementNo potential conflict of interest was reported by the author(s).Authors' contributionsShaowei Wang, Qizhi Fu, and Wenna Chen contributed equally to this work. Shaowei Wang, Wenna Chen, Qizhi Fu, Hongwei Jiang and Jincan Zhang conceptualised and designed the study. Qizhi Fu and Jincan Zhang provided the administrative support. Ganqin Du, Qizhi Fu, Jinghua Li and Xin Zhao provided the study materials. Jinghua Li, Xin Zhao collected and assembled the data. Shaowei Wang, Wenna Chen performed the data analysis and interpretation. Shaowei Wang, Wenna Chen, Qizhi Fu and Jincan Zhang wrote the manuscript. All authors approved the final manuscript.Data availability statementData used to support the findings of this study are available online at https://www.kaggle.com/datasets/plameneduardo/sarscov2-ctscan-dataset, and further inquiries can be directed to the corresponding author.Ethical approvalThis article uses the CT images, which were made publicly available by a research group as mentioned in 'Method'. Therefore, the authors of this study were not involved directly with human participants or animals.Additional informationFundingThe work was supported by the China Postdoctoral Science Foundation [2020M682285]; National Natural Science Foundation of China [31800836]; Medical and Health Research Project in Luoyang [2001027A]; Construction Project of Improving Medical Service Capacity of Provincial Medical Institutions in Henan Province [2017-51]; Project of Luoyang Science and Technology Bureau [2020YZ23].