A Hybrid of Fuzzy C-Means for the segmentation in CT scan and X-ray images for screening the COVID-19 patients

• Published in: Computer engineering and applications journal Vol. 13; no. 1; pp. 29 - 39
• Main Author: WangNo, Nitit
• Format: Journal Article
• Language: English
• Published: Palembang Computer Engineering and Applications Journal, Universitas Sriwijaya 01.02.2024
• Subjects: Accuracy; Algorithms; Artificial intelligence; Clustering; Computed tomography; Computer engineering; Coronaviruses; COVID-19; Efficiency; Entropy; Image segmentation; Information technology; Machine learning; Medical imaging; Pneumonia; X-rays
• ISSN: 2252-4274; 2252-5459; 2252-5459
• DOI: 10.18495/comengapp.v13i1.460

In this paper, using CT scan and X-ray images, we present a hybrid approach, based on combining fuzzy C-means with k-means clustering, to evaluate and determine pneumonia infection caused by the coronavirus disease (COVID-19). To achieve this objective, we introduce a hybrid method that combines fuzzy C-means clustering with K-means clustering. This hybrid approach is designed to effectively segment object boundaries within medical images, enabling the precise identification of pneumonia-related features. In addition to our hybrid method, we compare its performance with two other segmentation approaches: the Expectation Maximization (EM) algorithm and 2D Entropy segmentation. Which, the method we propose uses a comparison between the performances of the based on a database of medical imaging test. Experimental results showed that the proposed approach outperforms, it was found that the hybrid fuzzy C-means algorithm segmentation images methods give better performance in terms of accuracy, precision, and F-measure, which is effective in boundaries segmentation. Comparative results of the accuracy and image quality index demonstrate the robustness of AI. It also helps to improve work efficiency with accurate analysis of COVID-19 infection on CT scan and X-rays. In addition, the approach helps radiologists make clinical decisions for diagnosis, follow-up, and prognosis.