No abstract

No abstract

Malaria is a plasmodium parasite disease that affects millions of people in the world every year. Hence, early detection tests are needed to prevent the malaria parasites spread throughout the body. For centuries, manual microscopic blood test remains as the most common method that still being used for malaria detection. However, this procedure contains the probability of miscalculation of parasites due to human error. Computerized system is recognized as a quick and easy ways to analyze a lot of blood samples images by providing direct visualization on the computer screen without the need to examine under the microscope. Therefore, this paper aims to analyze different colour components for improving the parasites counting performance based on thick blood smear images. In this study, five different colour spaces namely YCbCr, RGB, CMY, HSV and HSL have been analyzed and eight colour components which are Y, Cb, R, G, C, M, S and L have been extracted in order to determine which colour component is the best for malaria parasites counting. Overall, experimental results indicate that segmentation using Y component of YCbCr proved to be the best with average counting accuracy of 98.48% for 100 images of malaria thick blood smear.

No abstract

Malaria is a pressing medical issue in tropical and subtropical regions. Currently, the manual microscopic examination remains the gold standard malaria diagnosis method. Nevertheless, this procedure required highly skilled lab technicians to prepare and examine the slides. Therefore, a framework encompassing image processing and machine learning is proposed due to inconsistencies in manual inspection, counting, and staging. Here, a standardized segmentation framework utilizing thresholding and clustering is developed to segment parasites’ stages of P. falciparum and P. vivax species. Moreover, a multi-stage classifier is designed for recognizing parasite species and staging in both species. Experimental results indicate the effectiveness of segmenting thick smear images based on Phansalkar thresholding garnered an accuracy of 99.86%. The employment of variance and new transferring process for the clustered members, enhanced k-means (EKM) clustering has successfully segmented all malaria stages with accuracy and an F1-score of 99.20% and 0.9033, respectively. In addition, the accuracies of parasite detection, species recognition, and staging obtained through a random forest (RF) accounted for 86.89%, 98.82%, and 90.78%, respectively, simultaneously. The proposed framework enables versatile malaria parasite detection and staging with an interactive result, paving the path for future improvements by utilizing the proposed framework on all others malaria species.