Adaptive fuzzy segmentation of 3D MR brain images

Alan Wee-Chung Liew; Hong Yan

doi:10.1109/FUZZ.2003.1206564

Adaptive fuzzy segmentation of 3D MR brain images

Alan Wee-Chung Liew
, Hong Yan

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

A fuzzy c-means based adaptive clustering algorithm is proposed for the fuzzy segmentation of 3D MR brain images, which are typically corrupted by noise and intensity non-uniformity (INU) artifact. The proposed algorithm enforces the spatial continuity constraint to account for the spatial correlations between image voxels, resulting in the suppression of noise and classification ambiguity. The INU artifact is compensated for by the introduction of a pseudo-3D bias field, which is modeled as a stack of smooth B-spline surfaces with continuity enforced across slices. The efficacy of the proposed algorithm is demonstrated experimentally using both simulated and real MR images. © 2003 IEEE

Original language	English
Title of host publication	Proceedings of the 12th IEEE International Conference on Fuzzy Systems
Publisher	IEEE
Pages	978-983
Volume	2
ISBN (Print)	0-7803-7810-5
DOIs	https://doi.org/10.1109/FUZZ.2003.1206564
Publication status	Published - 2003
Event	12th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2003) - St. Louis, United States Duration: 25 May 2003 → 28 May 2003

Conference

Conference	12th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2003)
Place	United States
City	St. Louis
Period	25/05/03 → 28/05/03

Access Output

10.1109/FUZZ.2003.1206564

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{7d3ab68f4d544b1889244ecd73475f5c,

title = "Adaptive fuzzy segmentation of 3D MR brain images",

abstract = "A fuzzy c-means based adaptive clustering algorithm is proposed for the fuzzy segmentation of 3D MR brain images, which are typically corrupted by noise and intensity non-uniformity (INU) artifact. The proposed algorithm enforces the spatial continuity constraint to account for the spatial correlations between image voxels, resulting in the suppression of noise and classification ambiguity. The INU artifact is compensated for by the introduction of a pseudo-3D bias field, which is modeled as a stack of smooth B-spline surfaces with continuity enforced across slices. The efficacy of the proposed algorithm is demonstrated experimentally using both simulated and real MR images. {\textcopyright} 2003 IEEE",

author = "Liew, \{Alan Wee-Chung\} and Hong Yan",

year = "2003",

doi = "10.1109/FUZZ.2003.1206564",

language = "English",

isbn = "0-7803-7810-5",

volume = "2",

pages = "978--983",

booktitle = "Proceedings of the 12th IEEE International Conference on Fuzzy Systems",

publisher = "IEEE",

address = "United States",

note = "12th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2003) ; Conference date: 25-05-2003 Through 28-05-2003",

}

TY - GEN

T1 - Adaptive fuzzy segmentation of 3D MR brain images

AU - Liew, Alan Wee-Chung

AU - Yan, Hong

PY - 2003

Y1 - 2003

N2 - A fuzzy c-means based adaptive clustering algorithm is proposed for the fuzzy segmentation of 3D MR brain images, which are typically corrupted by noise and intensity non-uniformity (INU) artifact. The proposed algorithm enforces the spatial continuity constraint to account for the spatial correlations between image voxels, resulting in the suppression of noise and classification ambiguity. The INU artifact is compensated for by the introduction of a pseudo-3D bias field, which is modeled as a stack of smooth B-spline surfaces with continuity enforced across slices. The efficacy of the proposed algorithm is demonstrated experimentally using both simulated and real MR images. © 2003 IEEE

AB - A fuzzy c-means based adaptive clustering algorithm is proposed for the fuzzy segmentation of 3D MR brain images, which are typically corrupted by noise and intensity non-uniformity (INU) artifact. The proposed algorithm enforces the spatial continuity constraint to account for the spatial correlations between image voxels, resulting in the suppression of noise and classification ambiguity. The INU artifact is compensated for by the introduction of a pseudo-3D bias field, which is modeled as a stack of smooth B-spline surfaces with continuity enforced across slices. The efficacy of the proposed algorithm is demonstrated experimentally using both simulated and real MR images. © 2003 IEEE

UR - https://www.scopus.com/pages/publications/0038537341

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0038537341&origin=recordpage

U2 - 10.1109/FUZZ.2003.1206564

DO - 10.1109/FUZZ.2003.1206564

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-7810-5

VL - 2

SP - 978

EP - 983

BT - Proceedings of the 12th IEEE International Conference on Fuzzy Systems

PB - IEEE

T2 - 12th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2003)

Y2 - 25 May 2003 through 28 May 2003

ER -

Adaptive fuzzy segmentation of 3D MR brain images

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this