Detection and Analysis of Malarial Parasites Using Microscopic Images  
  Authors : Ashok Sutkar; Marathe N. V.

 

Malaria is an infectious disease which is mainly diagnosed by visual microscopical evaluation of Giemsa stained blood smears. As it poses a serious global health problem, automation of the evaluation process is of high importance. The propose a set of features for distinguishing between non-infected red blood cells and cells infected by malaria parasites and evaluate the performance of these features on the set of red blood cells from the created database. The developed graphical user interface provides all tools necessary for creating a database of red blood cells. This approach proved to deliver good results on images with various qualitative characteristics resulting in only occasional over-segmented cells. The main part of this work is devoted to the extraction of features from the red blood cell images that could be used for distinguishing between infected and non-infected red blood cells. We propose a set of features based on shape, intensity, and texture and evaluate the performance of these features on the red blood cell samples from the created database using receiver operating characteristics. The results have shown that some of the features could be successfully used for malaria detection.

 

Published In : IJCAT Journal Volume 1, Issue 11

Date of Publication : 31 December 2014

Pages : 605 - 610

Figures :06

Tables : 02=

Publication Link :Detection and Analysis of Malarial Parasites Using Microscopic Images

 

 

 

Ashok Sutkar : Walchand College of Engineering, An Autonomous Institute, Sangli, Maharashtra, India

Marathe N. V. : Walchand College of Engineering, An Autonomous Institute, Sangli, Maharashtra, India

 

 

 

 

 

 

 

RBC Component

Microscopic images

Parasites

Feature Extraction

NN Classifier

SVM Classifier

Malaria is an infectious disease which is mainly diagnosed by visual microscopical evaluation of Giemsa stained blood smears. As it poses a serious global health problem, automation of the evaluation process is of high importance. The propose a set of features for distinguishing between non-infected red blood cells and cells infected by malaria parasites and evaluate the performance of these features on the set of red blood cells from the created database. The developed graphical user interface provides all tools necessary for creating a database of red blood cells. This approach proved to deliver good results on images with various qualitative characteristics resulting in only occasional over-segmented cells. The main part of this work is devoted to the extraction of features from the red blood cell images that could be used for distinguishing between infected and non-infected red blood cells. We propose a set of features based on shape, intensity, and texture and evaluate the performance of these features on the red blood cell samples from the created database using receiver operating characteristics. The results have shown that some of the features could be successfully used for malaria detection.

 

 

 

 

 

 

 

 

 

[1] Yashasvi Purwar, Sirish L Shah, Gwen Clarke, Areej Almugairi and Atis Muehlenbachs, “Automated and unsupervised detection of malarial parasites in microscopic images”, Purwar et al. Malaria Journal 2011, 10:3641,Department of Chemical and Materials Engineering, University of Alberta, Edmonton, Canada. [2] Pallavi T. Suradkar, “Detection of Malarial Parasite in Blood Using Image Processing”, International Journal of Engineering and Innovative Technology (IJEIT) Volume 2, Issue 10, April 2013A. [3] S.Abdul Nasir, M.Y.Mashor and Z.Mohamed, “Segmentation Based Approach for Detection of Malaria Parasites Using Moving K- Means Clustering”, Department of Medical Microbiology & Parasitology, School of Medical Sciences, Health Campus, Universiti Sains Malaysia, IEEE EMBS International Conference on Biomedical Engineering and Sciences, Langkawi, 17th - 19th December 2012. [4] S.Kareem, I.Kale and R.C.S Morling, “Automated Malaria Parasite Detection in Thin Blood Films:- A Hybrid Illumination and Color Constancy Insensitive, Morphological Approach”, IEEE Trans.on Applied DSP and VLSI Research Group University of Westminster London, United Kingdom, 2012. [5] Saowaluck Kaewkamnerd, Apichart Intarapanich, Montri Pannarat, Sastra Chaotheing, Chairat Uthaipibull and Sissades Tongsima, “Detection and Classification Device for Malaria Parasites in Thick- Blood Films” The 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications 15-17 September 2011, Prague, Czech Republic. [6] Sriram R., Meenalochani Chandar and Kota Srinivas, “Computer Aided Malarial Diagnosis for JSB Stained White Light Images Using Neural Networks", International Journal of Advanced Research in Computer Science and Software Engi-neering, Volume 3, Issue 8, August 2013, CSIR-CSIO, Chennai, India. [7] Isha Suwalka, Ankit Sanadhya, Anirudh Mathur and Mahendra S Chouhan, “Identify Malaria Parasite Using Pattern Recognition Technique” Geetanjali Institute of Technical Studies Dabok, Udaipur, India,2011. [8] Matthias Elter, Erik Haßlmeyer and Thorsten Zerfaß Fraunhofer, “Detection of malaria parasites in thick blood films”, Institute for Integrated Circuits IIS Image Processing and Medical Engineering Department Am Wolfsmantel 33, 91058 Erlangen, Germany, 33rd Annual International Conference of the IEEE EMBS Boston, Massachusetts USA, August 30 - September 3, 2011. [9] D. Anggraini, A. S. Nugroho, C. Pratama, et al., “Automated status identification of microscopic images obtained from malaria thin blood smears,” in 2011 International Conference on Electrical Engineering and Informatics (ICEEI), Bandung, Indonesia, 2011. [10] Amit Kumar, Manjunatha M, J Chatterjee and Ajoy K Ray, “Segmentation of Blood Smear Images using Normalized Cuts for Detection of Malarial Parasites” Dept. of Electronics & Electrical Communication Engineering, Annual IEEE India Conference (INDICON) 2010.