Breast density classification using a bag of features and an SVM classifier

M. Alhelou; M. Deriche; L. Ghouti

doi:10.1109/IEEEGCC.2017.8447974

Breast density classification using a bag of features and an SVM classifier

M. Alhelou
, M. Deriche
, L. Ghouti

King Fahd University of Petroleum and Minerals

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Breast cancer is one of the most common types of cancer, as well as the leading cause of mortality among women. Numerous attempts have been made in developing automated systems for identifying cancerous tissues from mammographic images. Breast density, in particular, is seen as the main characteristic used in Computer-Aided Diagnosis (CAD) systems. As such, breast density classification is seen as a crucial preprocessing stage in cancer detection. Here, we propose a new image preprocessing density classification approach for early detection of cancer from mammogram images using a set of robust texture and edge related features combined with an SVM classifier. The proposed algorithm achieves an accurate density classification of 93.56% for Low and High densities. The results were validated using the IRMA database. A comparison to state-of-the-art has been carried and showed that the proposed approach achieves improved performance in terms of density classification accuracy.

Original language	English
Title of host publication	2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781538627563
DOIs	https://doi.org/10.1109/IEEEGCC.2017.8447974
State	Published - 27 Aug 2018
Externally published	Yes
Event	9th IEEE-GCC Conference and Exhibition, GCCCE 2017 - Manama, Bahrain Duration: 8 May 2017 → 11 May 2017

Publication series

Name	2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017

Conference

Conference	9th IEEE-GCC Conference and Exhibition, GCCCE 2017
Country/Territory	Bahrain
City	Manama
Period	8/05/17 → 11/05/17

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Breast density classification
IRMA database
Mammograms
SMO-SVM
Texture features

Access to Document

10.1109/IEEEGCC.2017.8447974

Cite this

@inproceedings{86f8a6e15e3a469090b2605c9634e8e4,

title = "Breast density classification using a bag of features and an SVM classifier",

abstract = "Breast cancer is one of the most common types of cancer, as well as the leading cause of mortality among women. Numerous attempts have been made in developing automated systems for identifying cancerous tissues from mammographic images. Breast density, in particular, is seen as the main characteristic used in Computer-Aided Diagnosis (CAD) systems. As such, breast density classification is seen as a crucial preprocessing stage in cancer detection. Here, we propose a new image preprocessing density classification approach for early detection of cancer from mammogram images using a set of robust texture and edge related features combined with an SVM classifier. The proposed algorithm achieves an accurate density classification of 93.56\% for Low and High densities. The results were validated using the IRMA database. A comparison to state-of-the-art has been carried and showed that the proposed approach achieves improved performance in terms of density classification accuracy.",

keywords = "Breast density classification, IRMA database, Mammograms, SMO-SVM, Texture features",

author = "M. Alhelou and M. Deriche and L. Ghouti",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 9th IEEE-GCC Conference and Exhibition, GCCCE 2017 ; Conference date: 08-05-2017 Through 11-05-2017",

year = "2018",

month = aug,

day = "27",

doi = "10.1109/IEEEGCC.2017.8447974",

language = "English",

isbn = "9781538627563",

series = "2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017",

address = "United States",

}

Alhelou, M, Deriche, M & Ghouti, L 2018, Breast density classification using a bag of features and an SVM classifier. in 2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017., 8447974, 2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017, Institute of Electrical and Electronics Engineers Inc., 9th IEEE-GCC Conference and Exhibition, GCCCE 2017, Manama, Bahrain, 8/05/17. https://doi.org/10.1109/IEEEGCC.2017.8447974

Breast density classification using a bag of features and an SVM classifier. / Alhelou, M.; Deriche, M.; Ghouti, L.
2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017. Institute of Electrical and Electronics Engineers Inc., 2018. 8447974 (2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Breast density classification using a bag of features and an SVM classifier

AU - Alhelou, M.

AU - Deriche, M.

AU - Ghouti, L.

PY - 2018/8/27

Y1 - 2018/8/27

N2 - Breast cancer is one of the most common types of cancer, as well as the leading cause of mortality among women. Numerous attempts have been made in developing automated systems for identifying cancerous tissues from mammographic images. Breast density, in particular, is seen as the main characteristic used in Computer-Aided Diagnosis (CAD) systems. As such, breast density classification is seen as a crucial preprocessing stage in cancer detection. Here, we propose a new image preprocessing density classification approach for early detection of cancer from mammogram images using a set of robust texture and edge related features combined with an SVM classifier. The proposed algorithm achieves an accurate density classification of 93.56% for Low and High densities. The results were validated using the IRMA database. A comparison to state-of-the-art has been carried and showed that the proposed approach achieves improved performance in terms of density classification accuracy.

AB - Breast cancer is one of the most common types of cancer, as well as the leading cause of mortality among women. Numerous attempts have been made in developing automated systems for identifying cancerous tissues from mammographic images. Breast density, in particular, is seen as the main characteristic used in Computer-Aided Diagnosis (CAD) systems. As such, breast density classification is seen as a crucial preprocessing stage in cancer detection. Here, we propose a new image preprocessing density classification approach for early detection of cancer from mammogram images using a set of robust texture and edge related features combined with an SVM classifier. The proposed algorithm achieves an accurate density classification of 93.56% for Low and High densities. The results were validated using the IRMA database. A comparison to state-of-the-art has been carried and showed that the proposed approach achieves improved performance in terms of density classification accuracy.

KW - Breast density classification

KW - IRMA database

KW - Mammograms

KW - SMO-SVM

KW - Texture features

UR - https://www.scopus.com/pages/publications/85053927156

U2 - 10.1109/IEEEGCC.2017.8447974

DO - 10.1109/IEEEGCC.2017.8447974

M3 - Conference contribution

AN - SCOPUS:85053927156

SN - 9781538627563

T3 - 2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017

BT - 2017 9th IEEE-GCC Conference and Exhibition, GCCCE 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th IEEE-GCC Conference and Exhibition, GCCCE 2017

Y2 - 8 May 2017 through 11 May 2017

ER -

Breast density classification using a bag of features and an SVM classifier

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this