- Poster presentation
- Open Access
An automated system based on 2 d empirical mode decomposition and k-means clustering for classification of Plasmodium species in thin blood smear images
© Manickavasagam et al; licensee BioMed Central Ltd. 2014
- Published: 27 May 2014
- Plasmodium Falciparum
- Empirical Mode Decomposition
- Plasmodium Species
In order to control malarial infection, specific anti-malarial drug for the corresponding Plasmodium species must be administered. The objective of this work is to develop a system for classification of Plasmodium species in thin blood smear images.
In this work, thin blood smear sub images (n=87) of different Plasmodium species were acquired from the Parasite Image Library of the Centers for Disease Control and Prevention Database [http://www.dpd.cdc.gov/dpdx/HTML/ImageLibrary/Malaria_il.htm]. The images were subjected to 2 d Empirical Mode Decomposition and four features namely the mean value of first Intrinsic Mode Function (IMF-1), IMF-2, IMF-3 and residue, were extracted. The significance of the extracted features was analyzed using ANOVA test. Further, the k-means clustering algorithm was used to classify the different Plasmodium species using the significant features.
It was found that the features namely the mean of IMF-1 and residue are statistically significant (p<0.001) and the developed classification system was able to classify the Plasmodium vivax images with a high accuracy of 100%. Further, the Plasmodium malariae images were classified with an accuracy of 83.33%. However, the developed classifier showed lower accuracy in classification of Plasmodium falciparum and Plasmodium ovale images.
Results demonstrate that the developed system is highly efficient in classification of P. vivax and P. malariae. This study appears to be of high clinical relevance since the automated classification of malaria parasite is useful for mass screening and drug selection for treatment of the infection.
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.