Share Email Print

Proceedings Paper

Possibilistic-clustering-based MR brain image segmentation with accurate initialization
Author(s): Qingmin Liao; Yingying Deng; Weibei Dou; Su Ruan; Daniel Bloyet
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Magnetic resonance image analysis by computer is useful to aid diagnosis of malady. We present in this paper a automatic segmentation method for principal brain tissues. It is based on the possibilistic clustering approach, which is an improved fuzzy c-means clustering method. In order to improve the efficiency of clustering process, the initial value problem is discussed and solved by combining with a histogram analysis method. Our method can automatically determine number of classes to cluster and the initial values for each class. It has been tested on a set of forty MR brain images with or without the presence of tumor. The experimental results showed that it is simple, rapid and robust to segment the principal brain tissues.

Paper Details

Date Published: 18 January 2004
PDF: 5 pages
Proc. SPIE 5308, Visual Communications and Image Processing 2004, (18 January 2004); doi: 10.1117/12.526800
Show Author Affiliations
Qingmin Liao, Tsinghua Univ. (China)
Univ. de Caen (France)
Yingying Deng, Tsinghua Univ. (China)
Weibei Dou, Univ. de Caen (France)
Su Ruan, Univ. de Caen (France)
Daniel Bloyet, Univ. de Caen (France)

Published in SPIE Proceedings Vol. 5308:
Visual Communications and Image Processing 2004
Sethuraman Panchanathan; Bhaskaran Vasudev, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?