The lungs are one of the important and vital organs in the body that function as a respiratory system process. One way to detect lung disease is to do an X-rays test. Chest X-ray is a radiographic projection to detect abnormalities in lung organ by using x-ray radiation. In the process of diagnosing, doctors see the condition of the results of Chest X-rays in the form of a thorax image (chest) to know the patient has an abnormal or normal lung. However, doctors' diagnosis of chest X-rays results-based abnormalities is likely to differ depending on the doctor's abilities and experience. This problem is expected to be solved by segmenting the lung image to help make the diagnosis appropriately. The purpose of this study is to conduct an analysis that can differentiate abnormal and normal lungs. The process of recognition of these patterns consists of the pre-processing stage of image segmentation by using morphology and then proceed to grouping by using fuzzy c-means method to express the pattern of the already segmented image. This research produces normal and abnormal lung images that can be identified with an accuracy of 80%.
AFCM-LSMA: New Intelligent Model based on Lévy Slime Mould Algorithm and Adaptive Fuzzy C-means for Identification of COVID-19 Infection from Chest X-ray Images