Ulster University Logo

Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms

Rampun, Andrik, Morrow, Philip, Scotney, Bryan and Winder, John (2017) Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. In: Medical Image Understanding and Analysis 21st Annual Conference, MIUA 2017, Edinburgh, UK, July 11–13, 2017, Edinburgh. Springer. Vol 723 12 pp. [Conference contribution]

[img] Text (PDF) - Supplemental Material
Indefinitely restricted to Repository staff only.

24kB
[img] Text (PDF) - Accepted Version
818kB

URL: http://dx.doi.org/10.1007/978-3-319-60964-5

DOI: 10.1007/978-3-319-60964-5

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).

Item Type:Conference contribution (Paper)
Keywords:Breast density, local quinary patterns, classification, mammography
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Computing and Information Engineering
Faculty of Life and Health Sciences
Faculty of Life and Health Sciences > School of Health Sciences
Research Institutes and Groups:Institute of Nursing and Health Research > Centre for Health and Rehabilitation Technologies
Institute of Nursing and Health Research
Computer Science Research Institute
Computer Science Research Institute > Information and Communication Engineering
ID Code:38384
Deposited By: Professor Philip Morrow
Deposited On:26 Jul 2017 12:41
Last Modified:22 Jun 2018 22:23

Repository Staff Only: item control page