Automated classification of brain images using wavelet-energy and biogeography-based optimization

Gelan Yang; Yudong Zhang; Jiquan Yang; Genlin Ji; Zhengchao Dong; Shuihua Wang; Chunmei Feng; Qiong Wang

doi:10.1007/s11042-015-2649-7

Automated classification of brain images using wavelet-energy and biogeography-based optimization

Gelan Yang, Yudong Zhang^*, Jiquan Yang, Genlin Ji, Zhengchao Dong, Shuihua Wang, Chunmei Feng, Qiong Wang

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

149 Citations (Scopus)

Abstract

It is very important to early detect abnormal brains, in order to save social and hospital resources. The wavelet-energy was a successful feature descriptor that achieved excellent performances in various applications; hence, we proposed a novel wavelet-energy based approach for automated classification of MR brain images as normal or abnormal. SVM was used as the classifier, and biogeography-based optimization (BBO) was introduced to optimize the weights of the SVM. The results based on a 5 × 5-fold cross validation showed the performance of the proposed BBO-KSVM was superior to BP-NN, KSVM, and PSO-KSVM in terms of sensitivity and accuracy. The study offered a new means to detect abnormal brains with excellent performance.

Original language	English
Pages (from-to)	15601-15617
Number of pages	17
Journal	Multimedia Tools and Applications
Volume	75
Issue number	23
DOIs	https://doi.org/10.1007/s11042-015-2649-7
Publication status	Published - 1 Dec 2016
Externally published	Yes

Keywords

Biogeography-based optimization
Classification
Magnetic resonance imaging
Pattern recognition
Support vector machine

Access to Document

10.1007/s11042-015-2649-7

Cite this

@article{1fcc15e077fc40aa8c52ef1f0a9680d2,

title = "Automated classification of brain images using wavelet-energy and biogeography-based optimization",

abstract = "It is very important to early detect abnormal brains, in order to save social and hospital resources. The wavelet-energy was a successful feature descriptor that achieved excellent performances in various applications; hence, we proposed a novel wavelet-energy based approach for automated classification of MR brain images as normal or abnormal. SVM was used as the classifier, and biogeography-based optimization (BBO) was introduced to optimize the weights of the SVM. The results based on a 5 × 5-fold cross validation showed the performance of the proposed BBO-KSVM was superior to BP-NN, KSVM, and PSO-KSVM in terms of sensitivity and accuracy. The study offered a new means to detect abnormal brains with excellent performance.",

keywords = "Biogeography-based optimization, Classification, Magnetic resonance imaging, Pattern recognition, Support vector machine",

author = "Gelan Yang and Yudong Zhang and Jiquan Yang and Genlin Ji and Zhengchao Dong and Shuihua Wang and Chunmei Feng and Qiong Wang",

note = "Publisher Copyright: {\textcopyright} 2015, Springer Science+Business Media New York.",

year = "2016",

month = dec,

day = "1",

doi = "10.1007/s11042-015-2649-7",

language = "English",

volume = "75",

pages = "15601--15617",

journal = "Multimedia Tools and Applications",

issn = "1380-7501",

publisher = "Springer",

number = "23",

}

TY - JOUR

T1 - Automated classification of brain images using wavelet-energy and biogeography-based optimization

AU - Yang, Gelan

AU - Zhang, Yudong

AU - Yang, Jiquan

AU - Ji, Genlin

AU - Dong, Zhengchao

AU - Wang, Shuihua

AU - Feng, Chunmei

AU - Wang, Qiong

PY - 2016/12/1

Y1 - 2016/12/1

N2 - It is very important to early detect abnormal brains, in order to save social and hospital resources. The wavelet-energy was a successful feature descriptor that achieved excellent performances in various applications; hence, we proposed a novel wavelet-energy based approach for automated classification of MR brain images as normal or abnormal. SVM was used as the classifier, and biogeography-based optimization (BBO) was introduced to optimize the weights of the SVM. The results based on a 5 × 5-fold cross validation showed the performance of the proposed BBO-KSVM was superior to BP-NN, KSVM, and PSO-KSVM in terms of sensitivity and accuracy. The study offered a new means to detect abnormal brains with excellent performance.

AB - It is very important to early detect abnormal brains, in order to save social and hospital resources. The wavelet-energy was a successful feature descriptor that achieved excellent performances in various applications; hence, we proposed a novel wavelet-energy based approach for automated classification of MR brain images as normal or abnormal. SVM was used as the classifier, and biogeography-based optimization (BBO) was introduced to optimize the weights of the SVM. The results based on a 5 × 5-fold cross validation showed the performance of the proposed BBO-KSVM was superior to BP-NN, KSVM, and PSO-KSVM in terms of sensitivity and accuracy. The study offered a new means to detect abnormal brains with excellent performance.

KW - Biogeography-based optimization

KW - Classification

KW - Magnetic resonance imaging

KW - Pattern recognition

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84928688048&partnerID=8YFLogxK

U2 - 10.1007/s11042-015-2649-7

DO - 10.1007/s11042-015-2649-7

M3 - Article

AN - SCOPUS:84928688048

SN - 1380-7501

VL - 75

SP - 15601

EP - 15617

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

IS - 23

ER -

Automated classification of brain images using wavelet-energy and biogeography-based optimization

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this