Skip to main navigation Skip to search Skip to main content

Efficient fuzzy clustering based approach to brain tumor segmentation on MR images

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Image segmentation is one of the most vital and significant step in medical applications. The conventional fuzzy c-means (FCM) clustering is the most widely used unsupervised clustering method for brain tumor segmentation on magnetic resonance (MR) images. However, the major limitation of the conventional FCM is its huge computational time and it is sensitive to initial cluster centers. In this paper, we present a novel efficient FCM algorithm to eliminate the drawback of conventional FCM. The proposed algorithm is formulated by incorporating distribution of the gray level information in the image and a new objective function which ensures better stability and compactness of clusters. Experiments are conducted on brain MR images to investigate the effectiveness of the proposed method in segmenting brain tumor. The conventional FCM and the proposed method are compared to explore the efficiency and accuracy of the proposed method.

Original languageEnglish
Title of host publicationComputational Intelligence and Information Technology - First International Conference, CIIT 2011, Proceedings
Pages790-795
Number of pages6
DOIs
Publication statusPublished - 2011
Event1st International Conference on Computational Intelligence and Information Technology, CIIT 2011 - Pune, India
Duration: 07-11-201108-11-2011

Publication series

NameCommunications in Computer and Information Science
Volume250 CCIS
ISSN (Print)1865-0929

Conference

Conference1st International Conference on Computational Intelligence and Information Technology, CIIT 2011
Country/TerritoryIndia
CityPune
Period07-11-1108-11-11

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Efficient fuzzy clustering based approach to brain tumor segmentation on MR images'. Together they form a unique fingerprint.

Cite this