Edge-Based Segmentation for Accurate Detection of Malaria Parasites in Microscopic Blood Smear Images: A Novel Approach using FCM and MPP Algorithms

Abstract

Malaria is a significant global health communicable disease found in maximum epidemics areas, causing millions of cases of deaths including infant mortality each year. In this article, a segmentation technique is proposed to detect parasite cells of malaria in thin blood smear images using edge-based segmentation. Used gamma equalization to adjust lighting and the FCM soft clustering method to extract infected erythrocytes. The MPP algorithm was then used to improve edge-based segmentation. The proposed method achieved high accuracy, with SE, SP, PVP, and PVN values of 97.8%, 92.2%, 98.53%, and 91.38%, and MSER and F-measure values of 0.03 and 0.9, respectively. On the basis of the results, it can be inferred that the edge-based segmentation technique proposed in this study is capable of accurately segmenting red blood cells in blood smear images. This, in turn, can aid in the detection and segmentation of malaria parasites and facilitate the classification process.