CFP last date
22 April 2024
Reseach Article

Detection of Brain Tumor using Modified K Means Algorithm and SVM

Published on October 2013 by Labeed K Abdulgafoor, Aji George
National Conference on Recent Trends in Computer Applications
Foundation of Computer Science USA
NCRTCA - Number 1
October 2013
Authors: Labeed K Abdulgafoor, Aji George
b7269bb9-90c7-4a97-a697-68a63def174e

Labeed K Abdulgafoor, Aji George . Detection of Brain Tumor using Modified K Means Algorithm and SVM. National Conference on Recent Trends in Computer Applications. NCRTCA, 1 (October 2013), 28-31.

@article{
author = { Labeed K Abdulgafoor, Aji George },
title = { Detection of Brain Tumor using Modified K Means Algorithm and SVM },
journal = { National Conference on Recent Trends in Computer Applications },
issue_date = { October 2013 },
volume = { NCRTCA },
number = { 1 },
month = { October },
year = { 2013 },
issn = 0975-8887,
pages = { 28-31 },
numpages = 4,
url = { /proceedings/ncrtca/number1/13637-1309/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 National Conference on Recent Trends in Computer Applications
%A Labeed K Abdulgafoor
%A Aji George
%T Detection of Brain Tumor using Modified K Means Algorithm and SVM
%J National Conference on Recent Trends in Computer Applications
%@ 0975-8887
%V NCRTCA
%N 1
%P 28-31
%D 2013
%I International Journal of Computer Applications
Abstract

This paper presents a research on MRI images using wavelet transformation and modified K – means clustering for tumor segmentation. The first step is to perform image segmentation. It allows distinguishing masses and micro calcifications from background tissue. In this paper wavelet transformation and K- means clustering algorithm have been used for intensity based segmentation. The proposed algorithm is robust against noise. In this case, discrete wavelet transform (DWT) is used to extract high level details from MRI images. The processed image is added to the original image to get the sharpened image. Then modified K-means algorithm is applied to the sharpened image in which the tumor region can be located. . The combination of noise-robust nature of applied processes and the modified K-means algorithm, and SVM gives better results.

References
  1. Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing, Pearson Education, 2002. .
  2. Swati Tiwari, Ashish Bansal,Rupali Sagar. Identification of brain tumor using seeded region growing method. Journal of education. volume2, issue 1 Nov 2012
  3. Parisa Beham,Gurulakshmi. Morphological image processing approach on detection of tumour and cancer cells (2011) IEEE Trans, Image processing
  4. Ahmed, M. and D. B. Mohammad, 2008. Segmentation of Brain MR Images for Tumor Extraction by Combining K-means Clustering and Perona Malik Anisotropic Diffusion Model. International Journal of Image Processing, 2: 27-34.
  5. Mostafa, M. G. , M. F. Tolba, T. F. Gharib and M. A. Mageed, Medical Image Segmentation Using Wavelet Based Mutiresolution EM Algorithm.
  6. Hartigan, J. A. , Wong, M. A. : Algorithm AS136: A K-Means Clustering Algorithm. Applied Statistics 28, pp. 100–108 (1979).
  7. Abbasi S. and Mokhtarian F. (2001) IEEE Trans, Image processing, 10(1), 131-139.
  8. Abdel-Halim Elamy, Maidong Hu. (2007) IEEE Image Processing Society, 872-875.
  9. Bailet J. W. , Abemayor E. , Jabour B. A. , Hawkins R. A. , Hoh C. K. , Ward P. H. (1992) Laryngosope, 102, 281- 288.
Index Terms

Computer Science
Information Sciences

Keywords

Support Vector Mechine(svm) discrete Wavelet Transform(dwt) modified K Means Algorithm