DocumentCode :
2474694
Title :
A fuzzy C-means based algorithm for bias field estimation and segmentation of MR images
Author :
Yan, Bei ; Xie, Mei ; Gao, Jing-j Ing ; Zhao, Wei
Author_Institution :
Image Process. & Inf. Security Lab., UESTC, Chengdu, China
fYear :
2010
fDate :
17-19 Dec. 2010
Firstpage :
307
Lastpage :
310
Abstract :
This paper proposes a novel algorithm for simultaneous estimation of the bias field and segmentation of tissues for magnetic resonance images. The algorithm formulated by modifying the objective function in the fuzzy C-means algorithm to include a bias field which is modeled as a linear combination of a set of basis functions. Bias field estimation and image segmentation are simultaneously achieved as the result of minimizing this modified fuzzy C-means objective function. The iterative algorithm for objective function minimization we provide converges to the optimal solution at a fast rate. The outstanding advantages of our method are that its result is independent from initialization, which allows robust and fully automated application and the superior performance compared with other methods. The proposed method has been successfully applied to 3-Tesla MR images and got desirable results.
Keywords :
biomedical MRI; fuzzy set theory; image segmentation; iterative methods; medical image processing; pattern clustering; 3-Tesla MR images; bias field estimation; bias field segmentation; fuzzy C-means based algorithm; iterative algorithm; magnetic resonance images; objective function minimization; Convergence; Estimation; Image segmentation; Magnetic resonance; Nonhomogeneous media; Pixel; Robustness; bias field; fuzzy C-means; magnetic resonance image;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Apperceiving Computing and Intelligence Analysis (ICACIA), 2010 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-8025-8
Type :
conf
DOI :
10.1109/ICACIA.2010.5709907
Filename :
5709907
Link To Document :
بازگشت