Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm

Milad Azarbad, Ataollah Ebrahimzadeh, Abbas Babajani-Feremi

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

7 Citations (Scopus)

Abstract

Image thresholding is an important technique for image processing and pattern recognition. Several thresholding techniques have been proposed in the literature. In this paper for segmentation of magnetic resonance images, a novel method using a combination of the multilevel thresholding algorithm and the hierarchical evolutionary algorithm (HEA) is proposed. The HEA can be viewed as a variant of conventional genetic algorithms. The proposed technique is based on the participle swarm optimization (PSO) and, in fact, is an unsupervised clustering method based on an automatic multilevel thresholding approach. One advantage of the proposed method is that the number of clusters in the given image does not need to be known in advance. We evaluate and validate performance of the proposed method using simulation studies. The simulation results show that the accuracy of the proposed method is about 96%.

Original languageEnglish (US)
Title of host publication2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings
DOIs
StatePublished - Dec 1 2010
Externally publishedYes
Event17th Iranian Conference in Biomedical Engineering, ICBME 2010 - Isfahan, Iran, Islamic Republic of
Duration: Nov 3 2010Nov 4 2010

Other

Other17th Iranian Conference in Biomedical Engineering, ICBME 2010
CountryIran, Islamic Republic of
CityIsfahan
Period11/3/1011/4/10

Fingerprint

Evolutionary algorithms
Cluster Analysis
Brain
Tissue
Magnetic resonance
Pattern recognition
Image processing
Genetic algorithms
Magnetic Resonance Spectroscopy

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Physiology
  • Information Systems
  • Signal Processing

Cite this

Azarbad, M., Ebrahimzadeh, A., & Babajani-Feremi, A. (2010). Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm. In 2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings [5704938] https://doi.org/10.1109/ICBME.2010.5704938

Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm. / Azarbad, Milad; Ebrahimzadeh, Ataollah; Babajani-Feremi, Abbas.

2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings. 2010. 5704938.

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

Azarbad, M, Ebrahimzadeh, A & Babajani-Feremi, A 2010, Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm. in 2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings., 5704938, 17th Iranian Conference in Biomedical Engineering, ICBME 2010, Isfahan, Iran, Islamic Republic of, 11/3/10. https://doi.org/10.1109/ICBME.2010.5704938
Azarbad M, Ebrahimzadeh A, Babajani-Feremi A. Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm. In 2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings. 2010. 5704938 https://doi.org/10.1109/ICBME.2010.5704938
Azarbad, Milad ; Ebrahimzadeh, Ataollah ; Babajani-Feremi, Abbas. / Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm. 2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings. 2010.
@inproceedings{b53b55512ddd4471bdb43ae9ef8dec1a,
title = "Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm",
abstract = "Image thresholding is an important technique for image processing and pattern recognition. Several thresholding techniques have been proposed in the literature. In this paper for segmentation of magnetic resonance images, a novel method using a combination of the multilevel thresholding algorithm and the hierarchical evolutionary algorithm (HEA) is proposed. The HEA can be viewed as a variant of conventional genetic algorithms. The proposed technique is based on the participle swarm optimization (PSO) and, in fact, is an unsupervised clustering method based on an automatic multilevel thresholding approach. One advantage of the proposed method is that the number of clusters in the given image does not need to be known in advance. We evaluate and validate performance of the proposed method using simulation studies. The simulation results show that the accuracy of the proposed method is about 96{\%}.",
author = "Milad Azarbad and Ataollah Ebrahimzadeh and Abbas Babajani-Feremi",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/ICBME.2010.5704938",
language = "English (US)",
isbn = "9781424474844",
booktitle = "2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings",

}

TY - GEN

T1 - Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm

AU - Azarbad, Milad

AU - Ebrahimzadeh, Ataollah

AU - Babajani-Feremi, Abbas

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Image thresholding is an important technique for image processing and pattern recognition. Several thresholding techniques have been proposed in the literature. In this paper for segmentation of magnetic resonance images, a novel method using a combination of the multilevel thresholding algorithm and the hierarchical evolutionary algorithm (HEA) is proposed. The HEA can be viewed as a variant of conventional genetic algorithms. The proposed technique is based on the participle swarm optimization (PSO) and, in fact, is an unsupervised clustering method based on an automatic multilevel thresholding approach. One advantage of the proposed method is that the number of clusters in the given image does not need to be known in advance. We evaluate and validate performance of the proposed method using simulation studies. The simulation results show that the accuracy of the proposed method is about 96%.

AB - Image thresholding is an important technique for image processing and pattern recognition. Several thresholding techniques have been proposed in the literature. In this paper for segmentation of magnetic resonance images, a novel method using a combination of the multilevel thresholding algorithm and the hierarchical evolutionary algorithm (HEA) is proposed. The HEA can be viewed as a variant of conventional genetic algorithms. The proposed technique is based on the participle swarm optimization (PSO) and, in fact, is an unsupervised clustering method based on an automatic multilevel thresholding approach. One advantage of the proposed method is that the number of clusters in the given image does not need to be known in advance. We evaluate and validate performance of the proposed method using simulation studies. The simulation results show that the accuracy of the proposed method is about 96%.

UR - http://www.scopus.com/inward/record.url?scp=79951738375&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951738375&partnerID=8YFLogxK

U2 - 10.1109/ICBME.2010.5704938

DO - 10.1109/ICBME.2010.5704938

M3 - Conference contribution

SN - 9781424474844

BT - 2010 17th Iranian Conference of Biomedical Engineering, ICBME 2010 - Proceedings

ER -