Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms

Andrik Rampun, Philip Morrow, Bryan Scotney, John Winder

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper presents a method for breast density classifica- tion using local quinary patterns (LQP) in mammograms. LQP operators are used to capture the texture characteristics of the fibroglandular disk region (FGDroi) instead of the whole breast region as the majority of current studies have done. To maximise the local information, a mul- tiresolution approach is employed followed by dimensionality reduction by selecting dominant patterns only. 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 85.6% accuracy which is comparable with the state-of-the-art in the literature. Our contributions are two fold: firstly, we show the role of the fibroglandular disk area in representing the whole breast region as an im- portant region for more accurate density classification and secondly we show that the LQP operators can extract discriminative features com- parable with the other popular techniques such as local binary patterns, textons and local ternary patterns (LTP).
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsMaría Valdés Hernández, Victor González-Castro
Pages365-376
Number of pages12
Volume723
DOIs
Publication statusE-pub ahead of print - 22 Jun 2017
EventMedical Image Understanding and Analysis 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017 - Edinburgh
Duration: 22 Jun 2017 → …

Conference

ConferenceMedical Image Understanding and Analysis 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017
Period22/06/17 → …

Fingerprint

Support vector machines
Classifiers
Textures

Keywords

  • Breast density
  • local quinary patterns
  • classification
  • mammography

Cite this

Rampun, A., Morrow, P., Scotney, B., & Winder, J. (2017). Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. In M. Valdés Hernández, & V. González-Castro (Eds.), Unknown Host Publication (Vol. 723, pp. 365-376) https://doi.org/10.1007/978-3-319-60964-5
Rampun, Andrik ; Morrow, Philip ; Scotney, Bryan ; Winder, John. / Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. Unknown Host Publication. editor / María Valdés Hernández ; Victor González-Castro. Vol. 723 2017. pp. 365-376
@inproceedings{44d2c59e311f43ae9a1b00f182e091cb,
title = "Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms",
abstract = "This paper presents a method for breast density classifica- tion using local quinary patterns (LQP) in mammograms. LQP operators are used to capture the texture characteristics of the fibroglandular disk region (FGDroi) instead of the whole breast region as the majority of current studies have done. To maximise the local information, a mul- tiresolution approach is employed followed by dimensionality reduction by selecting dominant patterns only. 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 85.6{\%} accuracy which is comparable with the state-of-the-art in the literature. Our contributions are two fold: firstly, we show the role of the fibroglandular disk area in representing the whole breast region as an im- portant region for more accurate density classification and secondly we show that the LQP operators can extract discriminative features com- parable with the other popular techniques such as local binary patterns, textons and local ternary patterns (LTP).",
keywords = "Breast density, local quinary patterns, classification, mammography",
author = "Andrik Rampun and Philip Morrow and Bryan Scotney and John Winder",
year = "2017",
month = "6",
day = "22",
doi = "10.1007/978-3-319-60964-5",
language = "English",
isbn = "978-3-319-60964-5",
volume = "723",
pages = "365--376",
editor = "{Vald{\'e}s Hern{\'a}ndez}, Mar{\'i}a and Victor Gonz{\'a}lez-Castro",
booktitle = "Unknown Host Publication",

}

Rampun, A, Morrow, P, Scotney, B & Winder, J 2017, Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. in M Valdés Hernández & V González-Castro (eds), Unknown Host Publication. vol. 723, pp. 365-376, Medical Image Understanding and Analysis 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, 22/06/17. https://doi.org/10.1007/978-3-319-60964-5

Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. / Rampun, Andrik; Morrow, Philip; Scotney, Bryan; Winder, John.

Unknown Host Publication. ed. / María Valdés Hernández; Victor González-Castro. Vol. 723 2017. p. 365-376.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms

AU - Rampun, Andrik

AU - Morrow, Philip

AU - Scotney, Bryan

AU - Winder, John

PY - 2017/6/22

Y1 - 2017/6/22

N2 - This paper presents a method for breast density classifica- tion using local quinary patterns (LQP) in mammograms. LQP operators are used to capture the texture characteristics of the fibroglandular disk region (FGDroi) instead of the whole breast region as the majority of current studies have done. To maximise the local information, a mul- tiresolution approach is employed followed by dimensionality reduction by selecting dominant patterns only. 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 85.6% accuracy which is comparable with the state-of-the-art in the literature. Our contributions are two fold: firstly, we show the role of the fibroglandular disk area in representing the whole breast region as an im- portant region for more accurate density classification and secondly we show that the LQP operators can extract discriminative features com- parable with the other popular techniques such as local binary patterns, textons and local ternary patterns (LTP).

AB - This paper presents a method for breast density classifica- tion using local quinary patterns (LQP) in mammograms. LQP operators are used to capture the texture characteristics of the fibroglandular disk region (FGDroi) instead of the whole breast region as the majority of current studies have done. To maximise the local information, a mul- tiresolution approach is employed followed by dimensionality reduction by selecting dominant patterns only. 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 85.6% accuracy which is comparable with the state-of-the-art in the literature. Our contributions are two fold: firstly, we show the role of the fibroglandular disk area in representing the whole breast region as an im- portant region for more accurate density classification and secondly we show that the LQP operators can extract discriminative features com- parable with the other popular techniques such as local binary patterns, textons and local ternary patterns (LTP).

KW - Breast density

KW - local quinary patterns

KW - classification

KW - mammography

U2 - 10.1007/978-3-319-60964-5

DO - 10.1007/978-3-319-60964-5

M3 - Conference contribution

SN - 978-3-319-60964-5

VL - 723

SP - 365

EP - 376

BT - Unknown Host Publication

A2 - Valdés Hernández, María

A2 - González-Castro, Victor

ER -

Rampun A, Morrow P, Scotney B, Winder J. Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. In Valdés Hernández M, González-Castro V, editors, Unknown Host Publication. Vol. 723. 2017. p. 365-376 https://doi.org/10.1007/978-3-319-60964-5