A new brain MRI image segmentation strategy based on K-means clustering and SVM

Jianwei Liu; Lei Guo

doi:10.1109/IHMSC.2015.182

A new brain MRI image segmentation strategy based on K-means clustering and SVM

Jianwei Liu, Lei Guo

School of Automation

Northwestern Polytechnical University Xian

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

23 Scopus citations

Abstract

For the problem of noise and no reference image during brain magnetic resonance imagery (MRI) image segmentation, this paper proposes a new strategy to segment brain MRI image based on K-means clustering algorithm and support vector machine (SVM). Firstly, the strategy segments brain MRI image using K-means clustering algorithm to obtain the initial classification result as the class label, secondly, the feature vectors of each pixel of brain tissue are selected as the training samples and test samples, finally, brain MRI image is segmented by SVM. Experimental results show that the proposed segmentation strategy obtains better segmentation effect, especially has a good noise suppression for brain images with low signal-noise-ratio (SNR).

Original language	English
Title of host publication	Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	270-273
Number of pages	4
ISBN (Electronic)	9781479986460
DOIs	https://doi.org/10.1109/IHMSC.2015.182
State	Published - 20 Nov 2015
Event	7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015 - Hangzhou, Zhejiang, China Duration: 26 Aug 2015 → 27 Aug 2015

Publication series

Name	Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015
Volume	2

Conference

Conference	7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015
Country/Territory	China
City	Hangzhou, Zhejiang
Period	26/08/15 → 27/08/15

Keywords

Feature extraction
K-means clustering
Support vector machine (SVM)

Access to Document

10.1109/IHMSC.2015.182

Cite this

Liu, J., & Guo, L. (2015). A new brain MRI image segmentation strategy based on K-means clustering and SVM. In Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015 (pp. 270-273). Article 7334967 (Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015; Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IHMSC.2015.182

Liu, Jianwei ; Guo, Lei. / A new brain MRI image segmentation strategy based on K-means clustering and SVM. Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 270-273 (Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015).

@inproceedings{c27ae4edcecb4d138d1f69f532183bb5,

title = "A new brain MRI image segmentation strategy based on K-means clustering and SVM",

abstract = "For the problem of noise and no reference image during brain magnetic resonance imagery (MRI) image segmentation, this paper proposes a new strategy to segment brain MRI image based on K-means clustering algorithm and support vector machine (SVM). Firstly, the strategy segments brain MRI image using K-means clustering algorithm to obtain the initial classification result as the class label, secondly, the feature vectors of each pixel of brain tissue are selected as the training samples and test samples, finally, brain MRI image is segmented by SVM. Experimental results show that the proposed segmentation strategy obtains better segmentation effect, especially has a good noise suppression for brain images with low signal-noise-ratio (SNR).",

keywords = "Feature extraction, K-means clustering, Support vector machine (SVM)",

author = "Jianwei Liu and Lei Guo",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015 ; Conference date: 26-08-2015 Through 27-08-2015",

year = "2015",

month = nov,

day = "20",

doi = "10.1109/IHMSC.2015.182",

language = "英语",

series = "Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "270--273",

booktitle = "Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015",

}

Liu, J & Guo, L 2015, A new brain MRI image segmentation strategy based on K-means clustering and SVM. in Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015., 7334967, Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015, vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 270-273, 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015, Hangzhou, Zhejiang, China, 26/08/15. https://doi.org/10.1109/IHMSC.2015.182

A new brain MRI image segmentation strategy based on K-means clustering and SVM. / Liu, Jianwei; Guo, Lei.
Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 270-273 7334967 (Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new brain MRI image segmentation strategy based on K-means clustering and SVM

AU - Liu, Jianwei

AU - Guo, Lei

PY - 2015/11/20

Y1 - 2015/11/20

N2 - For the problem of noise and no reference image during brain magnetic resonance imagery (MRI) image segmentation, this paper proposes a new strategy to segment brain MRI image based on K-means clustering algorithm and support vector machine (SVM). Firstly, the strategy segments brain MRI image using K-means clustering algorithm to obtain the initial classification result as the class label, secondly, the feature vectors of each pixel of brain tissue are selected as the training samples and test samples, finally, brain MRI image is segmented by SVM. Experimental results show that the proposed segmentation strategy obtains better segmentation effect, especially has a good noise suppression for brain images with low signal-noise-ratio (SNR).

AB - For the problem of noise and no reference image during brain magnetic resonance imagery (MRI) image segmentation, this paper proposes a new strategy to segment brain MRI image based on K-means clustering algorithm and support vector machine (SVM). Firstly, the strategy segments brain MRI image using K-means clustering algorithm to obtain the initial classification result as the class label, secondly, the feature vectors of each pixel of brain tissue are selected as the training samples and test samples, finally, brain MRI image is segmented by SVM. Experimental results show that the proposed segmentation strategy obtains better segmentation effect, especially has a good noise suppression for brain images with low signal-noise-ratio (SNR).

KW - Feature extraction

KW - K-means clustering

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=84954436776&partnerID=8YFLogxK

U2 - 10.1109/IHMSC.2015.182

DO - 10.1109/IHMSC.2015.182

M3 - 会议稿件

AN - SCOPUS:84954436776

T3 - Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015

SP - 270

EP - 273

BT - Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015

Y2 - 26 August 2015 through 27 August 2015

ER -

Liu J, Guo L. A new brain MRI image segmentation strategy based on K-means clustering and SVM. In Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 270-273. 7334967. (Proceedings - 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2015). doi: 10.1109/IHMSC.2015.182

A new brain MRI image segmentation strategy based on K-means clustering and SVM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this