A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram

Mohamed Meselhy Eltoukhy; Ibrahima Faye; Brahim Belhaouari Samir

doi:10.1016/j.compbiomed.2010.02.002

A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram

Mohamed Meselhy Eltoukhy^*, Ibrahima Faye, Brahim Belhaouari Samir

^*Corresponding author for this work

Universiti Teknologi Petronas

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

122 Citations (Scopus)

Abstract

This paper presents a comparative study between wavelet and curvelet transform for breast cancer diagnosis in digital mammogram. Using multiresolution analysis, mammogram images are decomposed into different resolution levels, which are sensitive to different frequency bands. A set of the biggest coefficients from each decomposition level is extracted. Then a supervised classifier system based on Euclidian distance is constructed. The performance of the classifier is evaluated using a 2×5-fold cross validation followed by a statistical analysis. The experimental results suggest that curvelet transform outperforms wavelet transform and the difference is statistically significant.

Original language	English
Pages (from-to)	384-391
Number of pages	8
Journal	Computers in Biology and Medicine
Volume	40
Issue number	4
DOIs	https://doi.org/10.1016/j.compbiomed.2010.02.002
Publication status	Published - Apr 2010
Externally published	Yes

Keywords

Breast cancer
Curvelet
Digital mammogram
Feature extraction
Multiresolution
Wavelet

Access to Document

10.1016/j.compbiomed.2010.02.002

Cite this

@article{e7991ed04e564f49812e124c149ae62c,

title = "A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram",

abstract = "This paper presents a comparative study between wavelet and curvelet transform for breast cancer diagnosis in digital mammogram. Using multiresolution analysis, mammogram images are decomposed into different resolution levels, which are sensitive to different frequency bands. A set of the biggest coefficients from each decomposition level is extracted. Then a supervised classifier system based on Euclidian distance is constructed. The performance of the classifier is evaluated using a 2×5-fold cross validation followed by a statistical analysis. The experimental results suggest that curvelet transform outperforms wavelet transform and the difference is statistically significant.",

keywords = "Breast cancer, Curvelet, Digital mammogram, Feature extraction, Multiresolution, Wavelet",

author = "{Meselhy Eltoukhy}, Mohamed and Ibrahima Faye and {Belhaouari Samir}, Brahim",

year = "2010",

month = apr,

doi = "10.1016/j.compbiomed.2010.02.002",

language = "English",

volume = "40",

pages = "384--391",

journal = "Computers in Biology and Medicine",

issn = "0010-4825",

publisher = "Elsevier Ltd",

number = "4",

}

TY - JOUR

T1 - A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram

AU - Meselhy Eltoukhy, Mohamed

AU - Faye, Ibrahima

AU - Belhaouari Samir, Brahim

PY - 2010/4

Y1 - 2010/4

N2 - This paper presents a comparative study between wavelet and curvelet transform for breast cancer diagnosis in digital mammogram. Using multiresolution analysis, mammogram images are decomposed into different resolution levels, which are sensitive to different frequency bands. A set of the biggest coefficients from each decomposition level is extracted. Then a supervised classifier system based on Euclidian distance is constructed. The performance of the classifier is evaluated using a 2×5-fold cross validation followed by a statistical analysis. The experimental results suggest that curvelet transform outperforms wavelet transform and the difference is statistically significant.

AB - This paper presents a comparative study between wavelet and curvelet transform for breast cancer diagnosis in digital mammogram. Using multiresolution analysis, mammogram images are decomposed into different resolution levels, which are sensitive to different frequency bands. A set of the biggest coefficients from each decomposition level is extracted. Then a supervised classifier system based on Euclidian distance is constructed. The performance of the classifier is evaluated using a 2×5-fold cross validation followed by a statistical analysis. The experimental results suggest that curvelet transform outperforms wavelet transform and the difference is statistically significant.

KW - Breast cancer

KW - Curvelet

KW - Digital mammogram

KW - Feature extraction

KW - Multiresolution

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=77950859535&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2010.02.002

DO - 10.1016/j.compbiomed.2010.02.002

M3 - Article

C2 - 20163793

AN - SCOPUS:77950859535

SN - 0010-4825

VL - 40

SP - 384

EP - 391

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

IS - 4

ER -

A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this