A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme

Hesheng Wang, Baowei Fei

Research output: Contribution to journalArticle

85 Citations (Scopus)

Abstract

A fully automatic, multiscale fuzzy C-means (MsFCM) classification method for MR images is presented in this paper. We use a diffusion filter to process MR images and to construct a multiscale image series. A multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels. The objective function of the conventional fuzzy C-means (FCM) method is modified to allow multiscale classification processing where the result from a coarse scale supervises the classification in the next fine scale. The method is robust for noise and low-contrast MR images because of its multiscale diffusion filtering scheme. The new method was compared with the conventional FCM method and a modified FCM (MFCM) method. Validation studies were performed on synthesized images with various contrasts and on the McGill brain MR image database. Our MsFCM method consistently performed better than the conventional FCM and MFCM methods. The MsFCM method achieved an overlap ratio of greater than 90% as validated by the ground truth. Experiments results on real MR images were given to demonstrate the effectiveness of the proposed method. Our multiscale fuzzy C-means classification method is accurate and robust for various MR images. It can provide a quantitative tool for neuroimaging and other applications.

Original languageEnglish (US)
Pages (from-to)193-202
Number of pages10
JournalMedical Image Analysis
Volume13
Issue number2
DOIs
StatePublished - Apr 1 2009
Externally publishedYes

Fingerprint

Neuroimaging
Brain
Processing
Validation Studies
Experiments
Noise
Databases

Keywords

  • Fuzzy C-means
  • Image classification
  • Magnetic resonance imaging (MRI)
  • Multiscale diffusion filter
  • Neuroimaging

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology

Cite this

A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme. / Wang, Hesheng; Fei, Baowei.

In: Medical Image Analysis, Vol. 13, No. 2, 01.04.2009, p. 193-202.

Research output: Contribution to journalArticle

@article{82ce1f65dd244ad1a2baf0c2922ca569,
title = "A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme",
abstract = "A fully automatic, multiscale fuzzy C-means (MsFCM) classification method for MR images is presented in this paper. We use a diffusion filter to process MR images and to construct a multiscale image series. A multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels. The objective function of the conventional fuzzy C-means (FCM) method is modified to allow multiscale classification processing where the result from a coarse scale supervises the classification in the next fine scale. The method is robust for noise and low-contrast MR images because of its multiscale diffusion filtering scheme. The new method was compared with the conventional FCM method and a modified FCM (MFCM) method. Validation studies were performed on synthesized images with various contrasts and on the McGill brain MR image database. Our MsFCM method consistently performed better than the conventional FCM and MFCM methods. The MsFCM method achieved an overlap ratio of greater than 90{\%} as validated by the ground truth. Experiments results on real MR images were given to demonstrate the effectiveness of the proposed method. Our multiscale fuzzy C-means classification method is accurate and robust for various MR images. It can provide a quantitative tool for neuroimaging and other applications.",
keywords = "Fuzzy C-means, Image classification, Magnetic resonance imaging (MRI), Multiscale diffusion filter, Neuroimaging",
author = "Hesheng Wang and Baowei Fei",
year = "2009",
month = "4",
day = "1",
doi = "10.1016/j.media.2008.06.014",
language = "English (US)",
volume = "13",
pages = "193--202",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme

AU - Wang, Hesheng

AU - Fei, Baowei

PY - 2009/4/1

Y1 - 2009/4/1

N2 - A fully automatic, multiscale fuzzy C-means (MsFCM) classification method for MR images is presented in this paper. We use a diffusion filter to process MR images and to construct a multiscale image series. A multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels. The objective function of the conventional fuzzy C-means (FCM) method is modified to allow multiscale classification processing where the result from a coarse scale supervises the classification in the next fine scale. The method is robust for noise and low-contrast MR images because of its multiscale diffusion filtering scheme. The new method was compared with the conventional FCM method and a modified FCM (MFCM) method. Validation studies were performed on synthesized images with various contrasts and on the McGill brain MR image database. Our MsFCM method consistently performed better than the conventional FCM and MFCM methods. The MsFCM method achieved an overlap ratio of greater than 90% as validated by the ground truth. Experiments results on real MR images were given to demonstrate the effectiveness of the proposed method. Our multiscale fuzzy C-means classification method is accurate and robust for various MR images. It can provide a quantitative tool for neuroimaging and other applications.

AB - A fully automatic, multiscale fuzzy C-means (MsFCM) classification method for MR images is presented in this paper. We use a diffusion filter to process MR images and to construct a multiscale image series. A multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels. The objective function of the conventional fuzzy C-means (FCM) method is modified to allow multiscale classification processing where the result from a coarse scale supervises the classification in the next fine scale. The method is robust for noise and low-contrast MR images because of its multiscale diffusion filtering scheme. The new method was compared with the conventional FCM method and a modified FCM (MFCM) method. Validation studies were performed on synthesized images with various contrasts and on the McGill brain MR image database. Our MsFCM method consistently performed better than the conventional FCM and MFCM methods. The MsFCM method achieved an overlap ratio of greater than 90% as validated by the ground truth. Experiments results on real MR images were given to demonstrate the effectiveness of the proposed method. Our multiscale fuzzy C-means classification method is accurate and robust for various MR images. It can provide a quantitative tool for neuroimaging and other applications.

KW - Fuzzy C-means

KW - Image classification

KW - Magnetic resonance imaging (MRI)

KW - Multiscale diffusion filter

KW - Neuroimaging

UR - http://www.scopus.com/inward/record.url?scp=62549123629&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62549123629&partnerID=8YFLogxK

U2 - 10.1016/j.media.2008.06.014

DO - 10.1016/j.media.2008.06.014

M3 - Article

C2 - 18684658

AN - SCOPUS:62549123629

VL - 13

SP - 193

EP - 202

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 2

ER -