An Intelligent Recognition Procedure for Trophozoite Stages of Plasmodium Knowlesi Malaria
Keywords:
Image Processing, MLP, P. Knowlesi Malaria, Recognition, Thin Blood Smears,Abstract
Plasmodium (P.) Knowlesi is a fifth species of the malaria parasite in the world that caused a serious health problem. Current information suggests that P. Knowlesi is spread to people when an Anopheles mosquito infected by a monkey then bites and infects human (zoonotic transmission). Early identification of P. Knowlesi Malaria is an important step to an effective treatment. P. Knowlesi Malaria identification process is usually carried out with a 100x magnification of thin blood smear using microscope observation. However, this process is time-consuming and very tedious and strenuous for the human eyes. It also has a problem to differentiate between trophozoite, positive control (schizont and gametocyte) and negative control (white blood cell (WBC) and artefact). To overcome these situations, a computer-aided diagnosis system is developed to automatically identifying trophozoite stages of P. Knowlesi Malaria as early identification species, positive control and negative control. The processes involved starting from image acquisition, image processing and recognition. For image processing method, the most important part is the segmentation where the Otsu’s method is utilised to obtain the region of interest (ROI) of the infected cell. The features consist of the size of infected cell and size of the object. Finally, the recognition method using Multilayer Perceptron (MLP) is applied. The results show that the proposed automatic procedure is capable of recognising the trophozoite stage of P. Knowlesi Malaria with an accuracy of 98.70% for training and 97.67% for testing, using MLP trained by Lavernberg Marquardt (LM).Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Journal of Telecommunication, Electronic and Computer Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)