Saturation channel extraction of HSV color space for segmenting Plasmodium parasite

Malaria is one of the dangerous diseases in the world. Despite it has been decreased every year, the number of patients for this disease is still reasonably a lot. Technical problems that arise in the malaria cases are due to malaria examination and diagnosis analysis, which are carried out manually. At the same time, there are still medical personnel scarcities in some rural areas including of some districts in Indonesia. Moreover, the required examination process demands accuracy and takes a long time. Thus, an effective solution is necessary to help parasitologist to reduce malaria cases. One of the alternative ways to solve those problems is by utilizing technology to assist medical personnel in conducting examinations and analyzing the diagnosis results. This research was conducted to reach this objective. In achieving this objective, an image segmentation approach for finding the Plasmodium parasites was developed. The proposed approach consisted of four stages, which are the pre-processing stage, the segmentation stage, the refinement of segmentation results stage, and the evaluation stage. This proposed method was performed on 25 digital microscopy images of the thin blood smear digital microscopic images. The experiment yielded a good performance with the accuracy, sensitivity, and specificity of 99.83%, 85.06%, and 99.90%, respectively. These results indicate that the proposed method has an outstanding performance in segmenting Plasmodium parasite and can be utilized as a preliminary project to assist doctors in examining or identifying the Plasmodium parasites location.