Breast Density Classification Using Local Quinary Patterns with Various Neighbourhood Topologies

Andrik Rampun, Bryan Scotney, Philip Morrow, Hui Wang, John Winder

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper presents an extension of work from our previous study by investigating the use of Local Quinary Patterns (LQP) for breast density classification in mammograms on various neighbourhood topologies. The LQP operators are used to capture the texture characteristics of the fibro-glandular disk region (FGDroi) instead of the whole breast area as the majority of current studies have done. We take a multiresolution and multi-orientation approach, investigate the effects of various neighbourhood topologies and select dominant patterns to maximise texture information. Subsequently, the Support Vector Machine classifier is used to perform the classification, and a stratified ten-fold cross-validation scheme is employed to evaluate the performance of the method. The proposed method produced competitive results up to 86.13% and 82.02% accuracy based on 322 and 206 mammograms taken from the Mammographic Image Analysis Society (MIAS) and InBreast datasets, which is comparable with the state-of-the-art in the literature.
LanguageEnglish
Pages1-23
JournalJournal of Imaging
Volume4
Issue number14
DOIs
Publication statusPublished - 8 Jan 2018

Fingerprint

Textures
Topology
Image analysis
Support vector machines
Mathematical operators
Classifiers

Keywords

  • breast density classification
  • computer aided diagnosis
  • local quinary patterns
  • breast mammography

Cite this

@article{3dfbdafb606748ab8e5ab6b69c11d19f,
title = "Breast Density Classification Using Local Quinary Patterns with Various Neighbourhood Topologies",
abstract = "This paper presents an extension of work from our previous study by investigating the use of Local Quinary Patterns (LQP) for breast density classification in mammograms on various neighbourhood topologies. The LQP operators are used to capture the texture characteristics of the fibro-glandular disk region (FGDroi) instead of the whole breast area as the majority of current studies have done. We take a multiresolution and multi-orientation approach, investigate the effects of various neighbourhood topologies and select dominant patterns to maximise texture information. Subsequently, the Support Vector Machine classifier is used to perform the classification, and a stratified ten-fold cross-validation scheme is employed to evaluate the performance of the method. The proposed method produced competitive results up to 86.13{\%} and 82.02{\%} accuracy based on 322 and 206 mammograms taken from the Mammographic Image Analysis Society (MIAS) and InBreast datasets, which is comparable with the state-of-the-art in the literature.",
keywords = "breast density classification, computer aided diagnosis, local quinary patterns, breast mammography",
author = "Andrik Rampun and Bryan Scotney and Philip Morrow and Hui Wang and John Winder",
year = "2018",
month = "1",
day = "8",
doi = "10.3390/jimaging4010014",
language = "English",
volume = "4",
pages = "1--23",
journal = "Journal of Imaging",
issn = "2313-433X",
publisher = "MDPI",
number = "14",

}

Breast Density Classification Using Local Quinary Patterns with Various Neighbourhood Topologies. / Rampun, Andrik; Scotney, Bryan; Morrow, Philip; Wang, Hui; Winder, John.

In: Journal of Imaging, Vol. 4, No. 14, 08.01.2018, p. 1-23.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Breast Density Classification Using Local Quinary Patterns with Various Neighbourhood Topologies

AU - Rampun, Andrik

AU - Scotney, Bryan

AU - Morrow, Philip

AU - Wang, Hui

AU - Winder, John

PY - 2018/1/8

Y1 - 2018/1/8

N2 - This paper presents an extension of work from our previous study by investigating the use of Local Quinary Patterns (LQP) for breast density classification in mammograms on various neighbourhood topologies. The LQP operators are used to capture the texture characteristics of the fibro-glandular disk region (FGDroi) instead of the whole breast area as the majority of current studies have done. We take a multiresolution and multi-orientation approach, investigate the effects of various neighbourhood topologies and select dominant patterns to maximise texture information. Subsequently, the Support Vector Machine classifier is used to perform the classification, and a stratified ten-fold cross-validation scheme is employed to evaluate the performance of the method. The proposed method produced competitive results up to 86.13% and 82.02% accuracy based on 322 and 206 mammograms taken from the Mammographic Image Analysis Society (MIAS) and InBreast datasets, which is comparable with the state-of-the-art in the literature.

AB - This paper presents an extension of work from our previous study by investigating the use of Local Quinary Patterns (LQP) for breast density classification in mammograms on various neighbourhood topologies. The LQP operators are used to capture the texture characteristics of the fibro-glandular disk region (FGDroi) instead of the whole breast area as the majority of current studies have done. We take a multiresolution and multi-orientation approach, investigate the effects of various neighbourhood topologies and select dominant patterns to maximise texture information. Subsequently, the Support Vector Machine classifier is used to perform the classification, and a stratified ten-fold cross-validation scheme is employed to evaluate the performance of the method. The proposed method produced competitive results up to 86.13% and 82.02% accuracy based on 322 and 206 mammograms taken from the Mammographic Image Analysis Society (MIAS) and InBreast datasets, which is comparable with the state-of-the-art in the literature.

KW - breast density classification

KW - computer aided diagnosis

KW - local quinary patterns

KW - breast mammography

U2 - 10.3390/jimaging4010014

DO - 10.3390/jimaging4010014

M3 - Article

VL - 4

SP - 1

EP - 23

JO - Journal of Imaging

T2 - Journal of Imaging

JF - Journal of Imaging

SN - 2313-433X

IS - 14

ER -