Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi

Sezer Kutluk; Bilge Günsel

doi:10.1109/SIU.2013.6531255

Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi

Translated title of the contribution: Tissue density classification in mammographic images using local features

Sezer Kutluk
, Bilge Günsel

Department of Electronics and Communication Engineering

Istanbul Technical University

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

8 Citations (Scopus)

Abstract

In breast cancer cases, it is known that the ratio of correct diagnosis is affected by the breast tissue density. For this reason, automatic tissue density classification is an important process in diagnosis. In this work a method for classification of breast tissue density from mammographic images is proposed. The objective of the method is to determine which class, namely fatty, fatty-glandular and dense-glandular, the breast tissue belongs to. For this purpose, SIFT algorithm is used as the local feature extraction method, and LVQ algorithm is used for supervised classification. Test results on the MIAS dataset demonstrate that the code vectors corresponding to bag of SIFT features of each class can successfully model the breast tissue and the classification accuracy over 90% is achieved by LVQ.

Translated title of the contribution	Tissue density classification in mammographic images using local features
Original language	Turkish
Title of host publication	2013 21st Signal Processing and Communications Applications Conference, SIU 2013
DOIs	https://doi.org/10.1109/SIU.2013.6531255
Publication status	Published - 2013
Event	2013 21st Signal Processing and Communications Applications Conference, SIU 2013 - Haspolat, Turkey Duration: 24 Apr 2013 → 26 Apr 2013

Publication series

Name	2013 21st Signal Processing and Communications Applications Conference, SIU 2013

Conference

Conference	2013 21st Signal Processing and Communications Applications Conference, SIU 2013
Country/Territory	Turkey
City	Haspolat
Period	24/04/13 → 26/04/13

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/SIU.2013.6531255

Cite this

@inproceedings{927358bd225d4897b822ff1bea21ab87,

title = "Yerel {\"o}znitelikler ile mamografi g{\"o}r{\"u}nt{\"u}lerinde doku yoǧunluǧunun siniflandirilmasi",

abstract = "In breast cancer cases, it is known that the ratio of correct diagnosis is affected by the breast tissue density. For this reason, automatic tissue density classification is an important process in diagnosis. In this work a method for classification of breast tissue density from mammographic images is proposed. The objective of the method is to determine which class, namely fatty, fatty-glandular and dense-glandular, the breast tissue belongs to. For this purpose, SIFT algorithm is used as the local feature extraction method, and LVQ algorithm is used for supervised classification. Test results on the MIAS dataset demonstrate that the code vectors corresponding to bag of SIFT features of each class can successfully model the breast tissue and the classification accuracy over 90\% is achieved by LVQ.",

keywords = "Breast cancer, LVQ, Mammography, SIFT, Tissue density classification",

author = "Sezer Kutluk and Bilge G{\"u}nsel",

year = "2013",

doi = "10.1109/SIU.2013.6531255",

language = "T{\"u}rk{\c c}e",

isbn = "9781467355629",

series = "2013 21st Signal Processing and Communications Applications Conference, SIU 2013",

booktitle = "2013 21st Signal Processing and Communications Applications Conference, SIU 2013",

note = "2013 21st Signal Processing and Communications Applications Conference, SIU 2013 ; Conference date: 24-04-2013 Through 26-04-2013",

}

Kutluk, S & Günsel, B 2013, Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi. in 2013 21st Signal Processing and Communications Applications Conference, SIU 2013., 6531255, 2013 21st Signal Processing and Communications Applications Conference, SIU 2013, 2013 21st Signal Processing and Communications Applications Conference, SIU 2013, Haspolat, Turkey, 24/04/13. https://doi.org/10.1109/SIU.2013.6531255

Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi. / Kutluk, Sezer; Günsel, Bilge.
2013 21st Signal Processing and Communications Applications Conference, SIU 2013. 2013. 6531255 (2013 21st Signal Processing and Communications Applications Conference, SIU 2013).

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

TY - GEN

T1 - Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi

AU - Kutluk, Sezer

AU - Günsel, Bilge

PY - 2013

Y1 - 2013

N2 - In breast cancer cases, it is known that the ratio of correct diagnosis is affected by the breast tissue density. For this reason, automatic tissue density classification is an important process in diagnosis. In this work a method for classification of breast tissue density from mammographic images is proposed. The objective of the method is to determine which class, namely fatty, fatty-glandular and dense-glandular, the breast tissue belongs to. For this purpose, SIFT algorithm is used as the local feature extraction method, and LVQ algorithm is used for supervised classification. Test results on the MIAS dataset demonstrate that the code vectors corresponding to bag of SIFT features of each class can successfully model the breast tissue and the classification accuracy over 90% is achieved by LVQ.

AB - In breast cancer cases, it is known that the ratio of correct diagnosis is affected by the breast tissue density. For this reason, automatic tissue density classification is an important process in diagnosis. In this work a method for classification of breast tissue density from mammographic images is proposed. The objective of the method is to determine which class, namely fatty, fatty-glandular and dense-glandular, the breast tissue belongs to. For this purpose, SIFT algorithm is used as the local feature extraction method, and LVQ algorithm is used for supervised classification. Test results on the MIAS dataset demonstrate that the code vectors corresponding to bag of SIFT features of each class can successfully model the breast tissue and the classification accuracy over 90% is achieved by LVQ.

KW - Breast cancer

KW - LVQ

KW - Mammography

KW - SIFT

KW - Tissue density classification

UR - https://www.scopus.com/pages/publications/84880904628

U2 - 10.1109/SIU.2013.6531255

DO - 10.1109/SIU.2013.6531255

M3 - Konferans katkısı

AN - SCOPUS:84880904628

SN - 9781467355629

T3 - 2013 21st Signal Processing and Communications Applications Conference, SIU 2013

BT - 2013 21st Signal Processing and Communications Applications Conference, SIU 2013

T2 - 2013 21st Signal Processing and Communications Applications Conference, SIU 2013

Y2 - 24 April 2013 through 26 April 2013

ER -

Yerel öznitelikler ile mamografi görüntülerinde doku yoǧunluǧunun siniflandirilmasi

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this