Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

Shui Hua Wang; Tian Ming Zhan; Yi Chen; Yin Zhang; Ming Yang; Hui Min Lu; Hai Nan Wang; Bin Liu; Preetha Phillips

doi:10.1109/ACCESS.2016.2620996

Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

Shui Hua Wang, Tian Ming Zhan, Yi Chen^*, Yin Zhang, Ming Yang, Hui Min Lu, Hai Nan Wang, Bin Liu, Preetha Phillips

^*Corresponding author for this work

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

92 Citations (Scopus)

Abstract

To detect multiple sclerosis (MS) diseases early, we proposed a novel method on the hardware of magnetic resonance imaging, and on the software of three successful methods: biorthogonal wavelet transform, kernel principal component analysis, and logistic regression. The materials were 676 MR slices containing plaques from 38 MS patients, and 880 MR slices from 34 healthy controls. The statistical analysis showed our method achieved a sensitivity of 97.12±.14%, a specificity of 98.25±0.16%, and an accuracy of 97.76±0.10%. Our method is superior to five state-of-the-art approaches in MS detection.

Original language	English
Article number	7747672
Pages (from-to)	7567-7576
Number of pages	10
Journal	IEEE Access
Volume	4
DOIs	https://doi.org/10.1109/ACCESS.2016.2620996
Publication status	Published - 2016
Externally published	Yes

Keywords

Biorthogonal wavelet transform
Machine learning
computer vision
kernel principal component analysis
logistic regression
multiple sclerosis

Access to Document

10.1109/ACCESS.2016.2620996

Cite this

@article{8715abb96eb44dadbc28338ed64e5a43,

title = "Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression",

abstract = "To detect multiple sclerosis (MS) diseases early, we proposed a novel method on the hardware of magnetic resonance imaging, and on the software of three successful methods: biorthogonal wavelet transform, kernel principal component analysis, and logistic regression. The materials were 676 MR slices containing plaques from 38 MS patients, and 880 MR slices from 34 healthy controls. The statistical analysis showed our method achieved a sensitivity of 97.12±.14%, a specificity of 98.25±0.16%, and an accuracy of 97.76±0.10%. Our method is superior to five state-of-the-art approaches in MS detection.",

keywords = "Biorthogonal wavelet transform, Machine learning, computer vision, kernel principal component analysis, logistic regression, multiple sclerosis",

author = "Wang, {Shui Hua} and Zhan, {Tian Ming} and Yi Chen and Yin Zhang and Ming Yang and Lu, {Hui Min} and Wang, {Hai Nan} and Bin Liu and Preetha Phillips",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2016",

doi = "10.1109/ACCESS.2016.2620996",

language = "English",

volume = "4",

pages = "7567--7576",

journal = "IEEE Access",

issn = "2169-3536",

}

TY - JOUR

T1 - Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

AU - Wang, Shui Hua

AU - Zhan, Tian Ming

AU - Chen, Yi

AU - Zhang, Yin

AU - Yang, Ming

AU - Lu, Hui Min

AU - Wang, Hai Nan

AU - Liu, Bin

AU - Phillips, Preetha

PY - 2016

Y1 - 2016

N2 - To detect multiple sclerosis (MS) diseases early, we proposed a novel method on the hardware of magnetic resonance imaging, and on the software of three successful methods: biorthogonal wavelet transform, kernel principal component analysis, and logistic regression. The materials were 676 MR slices containing plaques from 38 MS patients, and 880 MR slices from 34 healthy controls. The statistical analysis showed our method achieved a sensitivity of 97.12±.14%, a specificity of 98.25±0.16%, and an accuracy of 97.76±0.10%. Our method is superior to five state-of-the-art approaches in MS detection.

AB - To detect multiple sclerosis (MS) diseases early, we proposed a novel method on the hardware of magnetic resonance imaging, and on the software of three successful methods: biorthogonal wavelet transform, kernel principal component analysis, and logistic regression. The materials were 676 MR slices containing plaques from 38 MS patients, and 880 MR slices from 34 healthy controls. The statistical analysis showed our method achieved a sensitivity of 97.12±.14%, a specificity of 98.25±0.16%, and an accuracy of 97.76±0.10%. Our method is superior to five state-of-the-art approaches in MS detection.

KW - Biorthogonal wavelet transform

KW - Machine learning

KW - computer vision

KW - kernel principal component analysis

KW - logistic regression

KW - multiple sclerosis

UR - http://www.scopus.com/inward/record.url?scp=85013218686&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2016.2620996

DO - 10.1109/ACCESS.2016.2620996

M3 - Article

AN - SCOPUS:85013218686

SN - 2169-3536

VL - 4

SP - 7567

EP - 7576

JO - IEEE Access

JF - IEEE Access

M1 - 7747672

ER -

Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this