A novel clustering method for quick partial volume estimation in MR brain images

Laszlo Szilagyi, Sandor Miklos Szilagyi, Balazs Benyo, Z. Benyó

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

Abstract

Automated brain MR image segmentation is a challenging pattern recognition problem that received significant attention lately. The most popular solutions involve fuzzy c-means (FCM) or similar clustering mechanisms. Several improvements have been made to the standard FCM algorithm, in order to reduce its sensitivity to Gaussian, impulse, and intensity non-uniformity noises. This paper presents a modified FCM-based method that targets accurate and fast segmentation in case of mixed noises. The proposed method extracts a scalar feature value from the neighbourhood of each pixel, using a context dependent filtering technique that deals with both spatial and grey level distances. These features are clustered afterwards by the histogram-based approach of the enhanced FCM algorithm. Results were evaluated based on synthetic phantoms and real MR images. Test experiments revealed that the proposed method provides better results compared to other reported FCM-based techniques. The time complexity of the proposed method is situated well below the traditional FCM algorithm. The achieved segmentation and the obtained fuzzy membership values represent excellent support for deformable contour model based cortical surface reconstruction methods.

Original languageEnglish
Title of host publicationIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume17
Edition1 PART 1
DOIs
Publication statusPublished - 2008
Event17th World Congress, International Federation of Automatic Control, IFAC - Seoul, Korea, Republic of
Duration: Jul 6 2008Jul 11 2008

Other

Other17th World Congress, International Federation of Automatic Control, IFAC
CountryKorea, Republic of
CitySeoul
Period7/6/087/11/08

Fingerprint

Brain
Surface reconstruction
Image segmentation
Pattern recognition
Pixels
Experiments

Keywords

  • Biomedical imaging systems

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Szilagyi, L., Szilagyi, S. M., Benyo, B., & Benyó, Z. (2008). A novel clustering method for quick partial volume estimation in MR brain images. In IFAC Proceedings Volumes (IFAC-PapersOnline) (1 PART 1 ed., Vol. 17) https://doi.org/10.3182/20080706-5-KR-1001.3746

A novel clustering method for quick partial volume estimation in MR brain images. / Szilagyi, Laszlo; Szilagyi, Sandor Miklos; Benyo, Balazs; Benyó, Z.

IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.

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

Szilagyi, L, Szilagyi, SM, Benyo, B & Benyó, Z 2008, A novel clustering method for quick partial volume estimation in MR brain images. in IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 edn, vol. 17, 17th World Congress, International Federation of Automatic Control, IFAC, Seoul, Korea, Republic of, 7/6/08. https://doi.org/10.3182/20080706-5-KR-1001.3746
Szilagyi L, Szilagyi SM, Benyo B, Benyó Z. A novel clustering method for quick partial volume estimation in MR brain images. In IFAC Proceedings Volumes (IFAC-PapersOnline). 1 PART 1 ed. Vol. 17. 2008 https://doi.org/10.3182/20080706-5-KR-1001.3746
Szilagyi, Laszlo ; Szilagyi, Sandor Miklos ; Benyo, Balazs ; Benyó, Z. / A novel clustering method for quick partial volume estimation in MR brain images. IFAC Proceedings Volumes (IFAC-PapersOnline). Vol. 17 1 PART 1. ed. 2008.
@inproceedings{d972d10a0c86402084df282c5cf8cfc3,
title = "A novel clustering method for quick partial volume estimation in MR brain images",
abstract = "Automated brain MR image segmentation is a challenging pattern recognition problem that received significant attention lately. The most popular solutions involve fuzzy c-means (FCM) or similar clustering mechanisms. Several improvements have been made to the standard FCM algorithm, in order to reduce its sensitivity to Gaussian, impulse, and intensity non-uniformity noises. This paper presents a modified FCM-based method that targets accurate and fast segmentation in case of mixed noises. The proposed method extracts a scalar feature value from the neighbourhood of each pixel, using a context dependent filtering technique that deals with both spatial and grey level distances. These features are clustered afterwards by the histogram-based approach of the enhanced FCM algorithm. Results were evaluated based on synthetic phantoms and real MR images. Test experiments revealed that the proposed method provides better results compared to other reported FCM-based techniques. The time complexity of the proposed method is situated well below the traditional FCM algorithm. The achieved segmentation and the obtained fuzzy membership values represent excellent support for deformable contour model based cortical surface reconstruction methods.",
keywords = "Biomedical imaging systems",
author = "Laszlo Szilagyi and Szilagyi, {Sandor Miklos} and Balazs Benyo and Z. Beny{\'o}",
year = "2008",
doi = "10.3182/20080706-5-KR-1001.3746",
language = "English",
isbn = "9783902661005",
volume = "17",
booktitle = "IFAC Proceedings Volumes (IFAC-PapersOnline)",
edition = "1 PART 1",

}

TY - GEN

T1 - A novel clustering method for quick partial volume estimation in MR brain images

AU - Szilagyi, Laszlo

AU - Szilagyi, Sandor Miklos

AU - Benyo, Balazs

AU - Benyó, Z.

PY - 2008

Y1 - 2008

N2 - Automated brain MR image segmentation is a challenging pattern recognition problem that received significant attention lately. The most popular solutions involve fuzzy c-means (FCM) or similar clustering mechanisms. Several improvements have been made to the standard FCM algorithm, in order to reduce its sensitivity to Gaussian, impulse, and intensity non-uniformity noises. This paper presents a modified FCM-based method that targets accurate and fast segmentation in case of mixed noises. The proposed method extracts a scalar feature value from the neighbourhood of each pixel, using a context dependent filtering technique that deals with both spatial and grey level distances. These features are clustered afterwards by the histogram-based approach of the enhanced FCM algorithm. Results were evaluated based on synthetic phantoms and real MR images. Test experiments revealed that the proposed method provides better results compared to other reported FCM-based techniques. The time complexity of the proposed method is situated well below the traditional FCM algorithm. The achieved segmentation and the obtained fuzzy membership values represent excellent support for deformable contour model based cortical surface reconstruction methods.

AB - Automated brain MR image segmentation is a challenging pattern recognition problem that received significant attention lately. The most popular solutions involve fuzzy c-means (FCM) or similar clustering mechanisms. Several improvements have been made to the standard FCM algorithm, in order to reduce its sensitivity to Gaussian, impulse, and intensity non-uniformity noises. This paper presents a modified FCM-based method that targets accurate and fast segmentation in case of mixed noises. The proposed method extracts a scalar feature value from the neighbourhood of each pixel, using a context dependent filtering technique that deals with both spatial and grey level distances. These features are clustered afterwards by the histogram-based approach of the enhanced FCM algorithm. Results were evaluated based on synthetic phantoms and real MR images. Test experiments revealed that the proposed method provides better results compared to other reported FCM-based techniques. The time complexity of the proposed method is situated well below the traditional FCM algorithm. The achieved segmentation and the obtained fuzzy membership values represent excellent support for deformable contour model based cortical surface reconstruction methods.

KW - Biomedical imaging systems

UR - http://www.scopus.com/inward/record.url?scp=79961017986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961017986&partnerID=8YFLogxK

U2 - 10.3182/20080706-5-KR-1001.3746

DO - 10.3182/20080706-5-KR-1001.3746

M3 - Conference contribution

SN - 9783902661005

VL - 17

BT - IFAC Proceedings Volumes (IFAC-PapersOnline)

ER -