Title: Diagnosis of pneumonia in the lungs in the conditions of the COVID-19 pandemic using ensemble learning methods
Authors: Fargana J. Abdullayeva; Suleyman Suleymanzade
Addresses: Institute of Information Technology, Azerbaijan National Academy of Sciences, 9A, B. Vahabzade Street, AZ1141, Baku, Azerbaijan ' Institute of Information Technology, Azerbaijan National Academy of Sciences, 9A, B. Vahabzade Street, AZ1141, Baku, Azerbaijan
Abstract: Chest X-ray (CXR) images play a significant role in the diagnosis of COVID-19 disease in pandemic conditions. However, one of the main problems in determining whether COVID-19 is negative or positive in medical imaging is that the classification models are prone to high false detection rates. The article proposes a system that can accurately assign chest X-ray images of COVID-19 to the appropriate COVID-19 and normal classes. The proposed system consists of two parts: 1) module for feature extraction from images; 2) ensemble learning module that performs the classification of images. Comparative analysis of the proposed approach with the existing methods is provided in numerous experiments, and the advantages of the proposed classification model and the feature extraction method from the previous methods are shown. A model as a result of the experiments, distinguished COVID-19 class images from normal images accurately. As ensemble learning strategies the bagging, pasting and AdaBoost techniques are used.
Keywords: chest X-ray image; COVID-19; medical images; pneumonia; ensemble learning.
International Journal of Reasoning-based Intelligent Systems, 2022 Vol.14 No.2/3, pp.114 - 122
Received: 25 Sep 2021
Accepted: 11 Apr 2022
Published online: 09 Sep 2022 *