Segmentation of Malaria Parasite Based on Stained Blood Cells Detection

Aimi Salihah Abdul-Nasir; Mohd Yusoff Mashor; Zeehaida Mohamed

doi:10.4028/www.scientific.net/JBBBE.24.43

Paper Titles

Effects of Various Carbon Nanotube Suspensions on A549, THP-1, and Peritoneal Macrophage Cells
p.1

Preparation and Characterization of an In Situ Hydrogel of Self-Assembly Type I Collagen from Shark Skin/Methylcellulose for Central Nerve System Regeneration
p.14

Directing Chondrogenesis of Primary Chondrocytes by Exposure to Glucose Concentrations
p.30

Segmentation of Malaria Parasite Based on Stained Blood Cells Detection
p.43

Optimum Gradation Direction for a Functionally Graded Endodontic Prefabricated Parallel Post: A Finite Element Method
p.56

Thermal Increasing Information for Foot Surface during Jogging
p.70

Inverse Kinematic Analysis of Three Link Mechanism for Fin Actuation of Fish Like Micro Device
p.77

Dynamic Analysis of IPMC Actuated Fin of a Micro Fish Like Device
p.82

Deflection Analysis of IPMC Actuated Fin of a Fish Like Micro Device
p.97

HomeJournal of Biomimetics, Biomaterials and...Journal of Biomimetics, Biomaterials and...Segmentation of Malaria Parasite Based on Stained...

Segmentation of Malaria Parasite Based on Stained Blood Cells Detection

Abstract:

Malaria is characterized by its life-threatening and destructive capability through the cause of widespread sufferings, contributing to the increase in mortality rates throughout the various parts of the world. Since the needs for immediate and appropriate diagnosis of malaria are urgently needed, this paper proposes a procedure for colour image segmentation that has been utilized using the malaria images of P. vivax species. First, the malaria images are enhanced by using modified global contrast stretching technique. Then, cascaded moving k-means and fuzzy c-means clustering is applied in order to segment the infected cell from its blood cells background. In this study, a new colour component namely modified B-Y component is proposed as a modified version of the original B-Y component of C-Y colour model. By using modified B-Y component, the colour properties of the infected cell component will be utilized for stained object identification in malaria image. The proposed colour component is compared to intensity, R-Y and B-Y components for identifying the component of colour that provides the best segmentation result. Finally, median filter and region growing algorithms are applied for smoothing the segmented image and removing any unwanted regions from the image, respectively. The proposed segmentation method has been applied and tested on 100 malaria images. The results indicate that segmentation using the proposed modified B-Y component has produced the best segmentation results with segmentation accuracy, sensitivity and specificity values of 99.37%, 88.22% and 99.82%, respectively.