Adaptive fuzzy segmentation of magnetic resonance images

Dzung L. Pham; Jerry L. Prince

doi:10.1109/42.802752

Adaptive fuzzy segmentation of magnetic resonance images

Dzung L. Pham, Jerry L. Prince

Whiting School of Engineering

Research output: Contribution to journal › Article › peer-review

692 Scopus citations

Abstract

An algorithm is presented for the fuzzy segmentation of two-dimensional (2-D) and three-dimensional (3-D) multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the 2-D adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new faster multigrid-based algorithm for its implementation. We show, using simulated MR data, that 3-D AFCM yields lower error rates than both the standard fuzzy C-means (FCM) algorithm and two other competing methods, when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.

Original language	English (US)
Pages (from-to)	737-752
Number of pages	16
Journal	IEEE transactions on medical imaging
Volume	18
Issue number	9
DOIs	https://doi.org/10.1109/42.802752
State	Published - Sep 1999

ASJC Scopus subject areas

Software
Radiological and Ultrasound Technology
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/42.802752

Cite this

@article{6b2a805b76e94352abdbb8fe10525e7b,

title = "Adaptive fuzzy segmentation of magnetic resonance images",

abstract = "An algorithm is presented for the fuzzy segmentation of two-dimensional (2-D) and three-dimensional (3-D) multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the 2-D adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new faster multigrid-based algorithm for its implementation. We show, using simulated MR data, that 3-D AFCM yields lower error rates than both the standard fuzzy C-means (FCM) algorithm and two other competing methods, when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.",

author = "Pham, {Dzung L.} and Prince, {Jerry L.}",

note = "Funding Information: Manuscript received August 10, 1998; revised August 8, 1999. This work was supported in part by the NSF under Presidential Faculty Grant MIP-9350336 and by the NIH under Grant 1RO1NS37747-01. The Associate Editor responsible for coordinating the review of this paper and recommending its publication was B. Vemuri. Asterisk indicates corresponding author.",

year = "1999",

month = sep,

doi = "10.1109/42.802752",

language = "English (US)",

volume = "18",

pages = "737--752",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "9",

}

TY - JOUR

T1 - Adaptive fuzzy segmentation of magnetic resonance images

AU - Pham, Dzung L.

AU - Prince, Jerry L.

N1 - Funding Information: Manuscript received August 10, 1998; revised August 8, 1999. This work was supported in part by the NSF under Presidential Faculty Grant MIP-9350336 and by the NIH under Grant 1RO1NS37747-01. The Associate Editor responsible for coordinating the review of this paper and recommending its publication was B. Vemuri. Asterisk indicates corresponding author.

PY - 1999/9

Y1 - 1999/9

N2 - An algorithm is presented for the fuzzy segmentation of two-dimensional (2-D) and three-dimensional (3-D) multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the 2-D adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new faster multigrid-based algorithm for its implementation. We show, using simulated MR data, that 3-D AFCM yields lower error rates than both the standard fuzzy C-means (FCM) algorithm and two other competing methods, when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.

AB - An algorithm is presented for the fuzzy segmentation of two-dimensional (2-D) and three-dimensional (3-D) multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the 2-D adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new faster multigrid-based algorithm for its implementation. We show, using simulated MR data, that 3-D AFCM yields lower error rates than both the standard fuzzy C-means (FCM) algorithm and two other competing methods, when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.

UR - http://www.scopus.com/inward/record.url?scp=0033181293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033181293&partnerID=8YFLogxK

U2 - 10.1109/42.802752

DO - 10.1109/42.802752

M3 - Article

C2 - 10571379

AN - SCOPUS:0033181293

SN - 0278-0062

VL - 18

SP - 737

EP - 752

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

IS - 9

ER -

Adaptive fuzzy segmentation of magnetic resonance images

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this