Volume and shape in feature space on adaptive FCM in MRI segmentation

Renjie He, Balasrinivasa Rao Sajja, Sushmita Datta, Ponnada A. Narayana

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

Original languageEnglish (US)
Pages (from-to)1580-1593
Number of pages14
JournalAnnals of biomedical engineering
Volume36
Issue number9
DOIs
StatePublished - Sep 1 2008

Fingerprint

Software packages
Cost functions
Magnetic resonance imaging
Brain
Polynomials
Tissue

Keywords

  • Adaptive FCM
  • Contextual constraints
  • Feature space
  • G-G algorithm
  • G-K algorithm
  • Inhomogeneity field
  • MRI
  • Multispectral segmentation
  • Shape
  • Volume

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Volume and shape in feature space on adaptive FCM in MRI segmentation. / He, Renjie; Sajja, Balasrinivasa Rao; Datta, Sushmita; Narayana, Ponnada A.

In: Annals of biomedical engineering, Vol. 36, No. 9, 01.09.2008, p. 1580-1593.

Research output: Contribution to journalArticle

He, Renjie ; Sajja, Balasrinivasa Rao ; Datta, Sushmita ; Narayana, Ponnada A. / Volume and shape in feature space on adaptive FCM in MRI segmentation. In: Annals of biomedical engineering. 2008 ; Vol. 36, No. 9. pp. 1580-1593.
@article{8181f942e3ee462982e53fc3ded26d7c,
title = "Volume and shape in feature space on adaptive FCM in MRI segmentation",
abstract = "Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.",
keywords = "Adaptive FCM, Contextual constraints, Feature space, G-G algorithm, G-K algorithm, Inhomogeneity field, MRI, Multispectral segmentation, Shape, Volume",
author = "Renjie He and Sajja, {Balasrinivasa Rao} and Sushmita Datta and Narayana, {Ponnada A.}",
year = "2008",
month = "9",
day = "1",
doi = "10.1007/s10439-008-9520-1",
language = "English (US)",
volume = "36",
pages = "1580--1593",
journal = "Annals of Biomedical Engineering",
issn = "0090-6964",
publisher = "Springer Netherlands",
number = "9",

}

TY - JOUR

T1 - Volume and shape in feature space on adaptive FCM in MRI segmentation

AU - He, Renjie

AU - Sajja, Balasrinivasa Rao

AU - Datta, Sushmita

AU - Narayana, Ponnada A.

PY - 2008/9/1

Y1 - 2008/9/1

N2 - Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

AB - Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

KW - Adaptive FCM

KW - Contextual constraints

KW - Feature space

KW - G-G algorithm

KW - G-K algorithm

KW - Inhomogeneity field

KW - MRI

KW - Multispectral segmentation

KW - Shape

KW - Volume

UR - http://www.scopus.com/inward/record.url?scp=49249132483&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49249132483&partnerID=8YFLogxK

U2 - 10.1007/s10439-008-9520-1

DO - 10.1007/s10439-008-9520-1

M3 - Article

C2 - 18574693

AN - SCOPUS:49249132483

VL - 36

SP - 1580

EP - 1593

JO - Annals of Biomedical Engineering

JF - Annals of Biomedical Engineering

SN - 0090-6964

IS - 9

ER -