A MR brain classification method based on multiscale and multiblock fuzzy C-means

Xiaofeng Yang, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

A fully automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with intensity correction for MR images is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and reducing the standard deviation of range function. We separate every scale image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels to overcome the effect of intensity inhomogeneity. The method is robust for noise MR images with intensity inhomogeneity because of its multiscale and multiblock bilateral filtering scheme. Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method on synthesized images, simulated brain MR images, and real MR images. The MsbFCM method achieved an overlap ratio of greater than 91% as validated by the ground truth even if original images have 9% noise and 40% intensity inhomogeneity. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images.

Original languageEnglish (US)
Title of host publication5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011
DOIs
StatePublished - Jul 14 2011
Externally publishedYes
Event5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011 - Wuhan, China
Duration: May 10 2011May 12 2011

Publication series

Name5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011

Conference

Conference5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011
CountryChina
CityWuhan
Period5/10/115/12/11

Fingerprint

Brain
Noise

Keywords

  • Bilateral filter
  • Fuzzy C-means (FCM)
  • Image classification
  • Magnetic resonance images (MRI)
  • Multiblock
  • Multiscale

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Yang, X., & Fei, B. (2011). A MR brain classification method based on multiscale and multiblock fuzzy C-means. In 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011 [5780357] (5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011). https://doi.org/10.1109/icbbe.2011.5780357

A MR brain classification method based on multiscale and multiblock fuzzy C-means. / Yang, Xiaofeng; Fei, Baowei.

5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011. 2011. 5780357 (5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yang, X & Fei, B 2011, A MR brain classification method based on multiscale and multiblock fuzzy C-means. in 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011., 5780357, 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011, 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011, Wuhan, China, 5/10/11. https://doi.org/10.1109/icbbe.2011.5780357
Yang X, Fei B. A MR brain classification method based on multiscale and multiblock fuzzy C-means. In 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011. 2011. 5780357. (5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011). https://doi.org/10.1109/icbbe.2011.5780357
Yang, Xiaofeng ; Fei, Baowei. / A MR brain classification method based on multiscale and multiblock fuzzy C-means. 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011. 2011. (5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011).
@inproceedings{f5fc73a5cb364a5fbf2c8e9ff06afcf5,
title = "A MR brain classification method based on multiscale and multiblock fuzzy C-means",
abstract = "A fully automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with intensity correction for MR images is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and reducing the standard deviation of range function. We separate every scale image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels to overcome the effect of intensity inhomogeneity. The method is robust for noise MR images with intensity inhomogeneity because of its multiscale and multiblock bilateral filtering scheme. Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method on synthesized images, simulated brain MR images, and real MR images. The MsbFCM method achieved an overlap ratio of greater than 91{\%} as validated by the ground truth even if original images have 9{\%} noise and 40{\%} intensity inhomogeneity. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images.",
keywords = "Bilateral filter, Fuzzy C-means (FCM), Image classification, Magnetic resonance images (MRI), Multiblock, Multiscale",
author = "Xiaofeng Yang and Baowei Fei",
year = "2011",
month = "7",
day = "14",
doi = "10.1109/icbbe.2011.5780357",
language = "English (US)",
isbn = "9781424450893",
series = "5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011",
booktitle = "5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011",

}

TY - GEN

T1 - A MR brain classification method based on multiscale and multiblock fuzzy C-means

AU - Yang, Xiaofeng

AU - Fei, Baowei

PY - 2011/7/14

Y1 - 2011/7/14

N2 - A fully automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with intensity correction for MR images is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and reducing the standard deviation of range function. We separate every scale image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels to overcome the effect of intensity inhomogeneity. The method is robust for noise MR images with intensity inhomogeneity because of its multiscale and multiblock bilateral filtering scheme. Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method on synthesized images, simulated brain MR images, and real MR images. The MsbFCM method achieved an overlap ratio of greater than 91% as validated by the ground truth even if original images have 9% noise and 40% intensity inhomogeneity. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images.

AB - A fully automatic, multiscale and multiblock fuzzy C-means (MsbFCM) classification method with intensity correction for MR images is presented in this paper. We use a bilateral filter to process MR images and to build a multiscale image series by increasing the standard deviation of spatial function and reducing the standard deviation of range function. We separate every scale image into multiple blocks and for every block a multiscale fuzzy C-means classification method is applied along the scales from the coarse to fine levels to overcome the effect of intensity inhomogeneity. The method is robust for noise MR images with intensity inhomogeneity because of its multiscale and multiblock bilateral filtering scheme. Our method was compared with the conventional FCM, a modified FCM (MFCM) and multiscale FCM (MsFCM) method on synthesized images, simulated brain MR images, and real MR images. The MsbFCM method achieved an overlap ratio of greater than 91% as validated by the ground truth even if original images have 9% noise and 40% intensity inhomogeneity. Experimental results using real MR images demonstrate the effectiveness of the proposed method. Our MsbFCM classification method is accurate and robust for various MR images.

KW - Bilateral filter

KW - Fuzzy C-means (FCM)

KW - Image classification

KW - Magnetic resonance images (MRI)

KW - Multiblock

KW - Multiscale

UR - http://www.scopus.com/inward/record.url?scp=79960126404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960126404&partnerID=8YFLogxK

U2 - 10.1109/icbbe.2011.5780357

DO - 10.1109/icbbe.2011.5780357

M3 - Conference contribution

C2 - 23358117

AN - SCOPUS:79960126404

SN - 9781424450893

T3 - 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011

BT - 5th International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2011

ER -