Adaptive FCM with contextual constrains for segmentation of multi-spectral MRI

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

Research output: Contribution to journalConference article

16 Citations (Scopus)

Abstract

An adaptive fuzzy c-means (FCM) clustering algorithm is explored for segmentation of three-dimensional multi-spectral MR images. This algorithm takes into consideration of both noise and three-dimensional intensity non-uniformity. This algorithm models the intensity non-uniformity of MR images as a gain field or bias field that slowly varies in space, which is approximated by a linear combination of smooth basis functions made up of polynomials with different orders. The contextual constraints are included by introducing a regularization term into the cost function of FCM. The regularization term is a measure of aggregation of local voxels that tend to overcome the noise in voxel labeling. We present our scheme both for bias and gain fields, with special attention is paid to robust estimation of the bias field.

Original languageEnglish (US)
Pages (from-to)1660-1663
Number of pages4
JournalAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume26 III
StatePublished - Dec 1 2004
EventConference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004 - San Francisco, CA, United States
Duration: Sep 1 2004Sep 5 2004

Fingerprint

Magnetic resonance imaging
Noise
Clustering algorithms
Cost functions
Labeling
Agglomeration
Polynomials
Cluster Analysis
Costs and Cost Analysis

Keywords

  • Adaptive
  • Bias field
  • Contextual Constraints
  • FCM
  • MRI
  • Multi-spectral
  • Segmentation

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Adaptive FCM with contextual constrains for segmentation of multi-spectral MRI. / He, Renjie; Datta, Sushmita; Sajja, Balasrinivasa Rao; Mehta, Meghana; Narayana, Ponnada A.

In: Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, Vol. 26 III, 01.12.2004, p. 1660-1663.

Research output: Contribution to journalConference article

@article{c828ae19b08b476ab2e69c01033be328,
title = "Adaptive FCM with contextual constrains for segmentation of multi-spectral MRI",
abstract = "An adaptive fuzzy c-means (FCM) clustering algorithm is explored for segmentation of three-dimensional multi-spectral MR images. This algorithm takes into consideration of both noise and three-dimensional intensity non-uniformity. This algorithm models the intensity non-uniformity of MR images as a gain field or bias field that slowly varies in space, which is approximated by a linear combination of smooth basis functions made up of polynomials with different orders. The contextual constraints are included by introducing a regularization term into the cost function of FCM. The regularization term is a measure of aggregation of local voxels that tend to overcome the noise in voxel labeling. We present our scheme both for bias and gain fields, with special attention is paid to robust estimation of the bias field.",
keywords = "Adaptive, Bias field, Contextual Constraints, FCM, MRI, Multi-spectral, Segmentation",
author = "Renjie He and Sushmita Datta and Sajja, {Balasrinivasa Rao} and Meghana Mehta and Narayana, {Ponnada A.}",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
volume = "26 III",
pages = "1660--1663",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Adaptive FCM with contextual constrains for segmentation of multi-spectral MRI

AU - He, Renjie

AU - Datta, Sushmita

AU - Sajja, Balasrinivasa Rao

AU - Mehta, Meghana

AU - Narayana, Ponnada A.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - An adaptive fuzzy c-means (FCM) clustering algorithm is explored for segmentation of three-dimensional multi-spectral MR images. This algorithm takes into consideration of both noise and three-dimensional intensity non-uniformity. This algorithm models the intensity non-uniformity of MR images as a gain field or bias field that slowly varies in space, which is approximated by a linear combination of smooth basis functions made up of polynomials with different orders. The contextual constraints are included by introducing a regularization term into the cost function of FCM. The regularization term is a measure of aggregation of local voxels that tend to overcome the noise in voxel labeling. We present our scheme both for bias and gain fields, with special attention is paid to robust estimation of the bias field.

AB - An adaptive fuzzy c-means (FCM) clustering algorithm is explored for segmentation of three-dimensional multi-spectral MR images. This algorithm takes into consideration of both noise and three-dimensional intensity non-uniformity. This algorithm models the intensity non-uniformity of MR images as a gain field or bias field that slowly varies in space, which is approximated by a linear combination of smooth basis functions made up of polynomials with different orders. The contextual constraints are included by introducing a regularization term into the cost function of FCM. The regularization term is a measure of aggregation of local voxels that tend to overcome the noise in voxel labeling. We present our scheme both for bias and gain fields, with special attention is paid to robust estimation of the bias field.

KW - Adaptive

KW - Bias field

KW - Contextual Constraints

KW - FCM

KW - MRI

KW - Multi-spectral

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=11144283666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144283666&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:11144283666

VL - 26 III

SP - 1660

EP - 1663

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -