Wavelet energy entropy and linear regression classifier for detecting abnormal breasts

Yi Chen; Yin Zhang; Hui Min Lu; Xian Qing Chen; Jian Wu Li; Shui Hua Wang

doi:10.1007/s11042-016-4161-0

Wavelet energy entropy and linear regression classifier for detecting abnormal breasts

Yi Chen, Yin Zhang, Hui Min Lu, Xian Qing Chen, Jian Wu Li, Shui Hua Wang^*

^*Corresponding author for this work

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

30 Citations (Scopus)

Abstract

Breast abnormalities are the early symptoms of breast cancers. They may also bring in psychoemotional stresses to women. In this study, we developed a new automatic program based on wavelet energy entropy (WEE) and linear regression classifier (LRC): First, we segment region of interest from mammogram images. Second, we calculate WEE from the segmented images. Third, LRC was used as the classifier. We named our method as “WEE + LRC”. The experiment used 10-fold stratified cross validation that was repeated 10 times. The statistical results showed the classification result was the best when the decomposition level was 4, with a sensitivity of 92.00 ± 3.20%, a specificity of 91.70 ± 3.27%, and an accuracy of 91.85 ± 2.21%. The proposed method was superior to other five state-of-the-art methods. In all, our method is effective in detecting abnormal breasts.

Original language	English
Pages (from-to)	3813-3832
Number of pages	20
Journal	Multimedia Tools and Applications
Volume	77
Issue number	3
DOIs	https://doi.org/10.1007/s11042-016-4161-0
Publication status	Published - 1 Feb 2018
Externally published	Yes

Keywords

Breast abnormality
Digital mammography
Least-squares estimation
Linear regression classifier
Wavelet energy entropy

Access to Document

10.1007/s11042-016-4161-0

Cite this

@article{c0a243a3f1e24fe1ac1ff529ebb82367,

title = "Wavelet energy entropy and linear regression classifier for detecting abnormal breasts",

abstract = "Breast abnormalities are the early symptoms of breast cancers. They may also bring in psychoemotional stresses to women. In this study, we developed a new automatic program based on wavelet energy entropy (WEE) and linear regression classifier (LRC): First, we segment region of interest from mammogram images. Second, we calculate WEE from the segmented images. Third, LRC was used as the classifier. We named our method as “WEE + LRC”. The experiment used 10-fold stratified cross validation that was repeated 10 times. The statistical results showed the classification result was the best when the decomposition level was 4, with a sensitivity of 92.00 ± 3.20%, a specificity of 91.70 ± 3.27%, and an accuracy of 91.85 ± 2.21%. The proposed method was superior to other five state-of-the-art methods. In all, our method is effective in detecting abnormal breasts.",

keywords = "Breast abnormality, Digital mammography, Least-squares estimation, Linear regression classifier, Wavelet energy entropy",

author = "Yi Chen and Yin Zhang and Lu, {Hui Min} and Chen, {Xian Qing} and Li, {Jian Wu} and Wang, {Shui Hua}",

note = "Publisher Copyright: {\textcopyright} 2016, Springer Science+Business Media New York.",

year = "2018",

month = feb,

day = "1",

doi = "10.1007/s11042-016-4161-0",

language = "English",

volume = "77",

pages = "3813--3832",

journal = "Multimedia Tools and Applications",

issn = "1380-7501",

publisher = "Springer",

number = "3",

}

TY - JOUR

T1 - Wavelet energy entropy and linear regression classifier for detecting abnormal breasts

AU - Chen, Yi

AU - Zhang, Yin

AU - Lu, Hui Min

AU - Chen, Xian Qing

AU - Li, Jian Wu

AU - Wang, Shui Hua

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Breast abnormalities are the early symptoms of breast cancers. They may also bring in psychoemotional stresses to women. In this study, we developed a new automatic program based on wavelet energy entropy (WEE) and linear regression classifier (LRC): First, we segment region of interest from mammogram images. Second, we calculate WEE from the segmented images. Third, LRC was used as the classifier. We named our method as “WEE + LRC”. The experiment used 10-fold stratified cross validation that was repeated 10 times. The statistical results showed the classification result was the best when the decomposition level was 4, with a sensitivity of 92.00 ± 3.20%, a specificity of 91.70 ± 3.27%, and an accuracy of 91.85 ± 2.21%. The proposed method was superior to other five state-of-the-art methods. In all, our method is effective in detecting abnormal breasts.

AB - Breast abnormalities are the early symptoms of breast cancers. They may also bring in psychoemotional stresses to women. In this study, we developed a new automatic program based on wavelet energy entropy (WEE) and linear regression classifier (LRC): First, we segment region of interest from mammogram images. Second, we calculate WEE from the segmented images. Third, LRC was used as the classifier. We named our method as “WEE + LRC”. The experiment used 10-fold stratified cross validation that was repeated 10 times. The statistical results showed the classification result was the best when the decomposition level was 4, with a sensitivity of 92.00 ± 3.20%, a specificity of 91.70 ± 3.27%, and an accuracy of 91.85 ± 2.21%. The proposed method was superior to other five state-of-the-art methods. In all, our method is effective in detecting abnormal breasts.

KW - Breast abnormality

KW - Digital mammography

KW - Least-squares estimation

KW - Linear regression classifier

KW - Wavelet energy entropy

UR - http://www.scopus.com/inward/record.url?scp=84996528863&partnerID=8YFLogxK

U2 - 10.1007/s11042-016-4161-0

DO - 10.1007/s11042-016-4161-0

M3 - Article

AN - SCOPUS:84996528863

SN - 1380-7501

VL - 77

SP - 3813

EP - 3832

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

IS - 3

ER -

Wavelet energy entropy and linear regression classifier for detecting abnormal breasts

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this