Round Randomized Learning Vector Quantization for Brain Tumor Imaging

Siti Norul Huda Sheikh Abdullah, Farah Aqilah Bohani, Baher H. Nayef, Shahnorbanun Sahran, Omar Al Akash, Rizuana Iqbal Hussain, Fuad Ismail

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.

Original languageEnglish
Article number8603609
JournalComputational and Mathematical Methods in Medicine
Volume2016
DOIs
Publication statusPublished - 2016

Fingerprint

Learning Vector Quantization
Brain Tumor
Vector quantization
Neuroimaging
Brain Neoplasms
Tumors
Brain
Imaging
Learning
Imaging techniques
Magnetic resonance
Distance Function
Euclidean Distance
Competitive Learning
Magnetic Resonance Image
Malaysia
Codebook
Model Fitting
Medical Imaging
Magnetic Resonance Imaging

ASJC Scopus subject areas

  • Applied Mathematics
  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)
  • Immunology and Microbiology(all)

Cite this

Round Randomized Learning Vector Quantization for Brain Tumor Imaging. / Sheikh Abdullah, Siti Norul Huda; Bohani, Farah Aqilah; Nayef, Baher H.; Sahran, Shahnorbanun; Al Akash, Omar; Iqbal Hussain, Rizuana; Ismail, Fuad.

In: Computational and Mathematical Methods in Medicine, Vol. 2016, 8603609, 2016.

Research output: Contribution to journalArticle

@article{4d38818c972748938866ad8c51b1b5c9,
title = "Round Randomized Learning Vector Quantization for Brain Tumor Imaging",
abstract = "Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.",
author = "{Sheikh Abdullah}, {Siti Norul Huda} and Bohani, {Farah Aqilah} and Nayef, {Baher H.} and Shahnorbanun Sahran and {Al Akash}, Omar and {Iqbal Hussain}, Rizuana and Fuad Ismail",
year = "2016",
doi = "10.1155/2016/8603609",
language = "English",
volume = "2016",
journal = "Computational and Mathematical Methods in Medicine",
issn = "1748-670X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Round Randomized Learning Vector Quantization for Brain Tumor Imaging

AU - Sheikh Abdullah, Siti Norul Huda

AU - Bohani, Farah Aqilah

AU - Nayef, Baher H.

AU - Sahran, Shahnorbanun

AU - Al Akash, Omar

AU - Iqbal Hussain, Rizuana

AU - Ismail, Fuad

PY - 2016

Y1 - 2016

N2 - Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.

AB - Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.

UR - http://www.scopus.com/inward/record.url?scp=84982812645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982812645&partnerID=8YFLogxK

U2 - 10.1155/2016/8603609

DO - 10.1155/2016/8603609

M3 - Article

C2 - 27516807

AN - SCOPUS:84982812645

VL - 2016

JO - Computational and Mathematical Methods in Medicine

JF - Computational and Mathematical Methods in Medicine

SN - 1748-670X

M1 - 8603609

ER -