A fuzzy C-means based algorithm for bias field estimation and segmentation of MR images

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...

Full description

Saved in:
Bibliographic Details
Published in2010 International Conference on Apperceiving Computing and Intelligence Analysis pp. 307 - 310
Main Authors Bei Yan, Mei Xie, Jing-Jing Gao, Wei Zhao
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2010
Subjects
bias field
Convergence
Estimation
fuzzy C-means
Image segmentation
Magnetic resonance
magnetic resonance image
Nonhomogeneous media
Pixel
Robustness
Online AccessGet full text
ISBN9781424480258
1424480256
DOI10.1109/ICACIA.2010.5709907

Cover

More Information
Summary: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.
ISBN:9781424480258
1424480256
DOI:10.1109/ICACIA.2010.5709907