A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography

Andrik Rampun, PJ Morrow, BW Scotney, RJ Winder

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

3 Citations (Scopus)

Abstract

This paper presents a preliminary quantitative study for breast cancer risk assessment in mammography using mathematical operators called Local Ternary Patterns. The study covers three different mapping patterns namely uniform (‘u2’), nonuniform (‘ri’) and a combination of uniform and nonuniform (‘riu2’). These patterns are used as texture features to model the appearance of breast density within the fibroglandular disk area. Subsequently, the Support Vector Machine is employed as a classification approach and initial results suggest that the mapping pattern ‘riu2’ outperforms the others.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages283-286
Number of pages4
Volume71
DOIs
Publication statusE-pub ahead of print - 21 May 2017
EventInternational Conference on Innovation in Medicine and Healthcare 2017 - Vilamoura, Portugal
Duration: 21 May 2017 → …

Conference

ConferenceInternational Conference on Innovation in Medicine and Healthcare 2017
Period21/05/17 → …

Fingerprint

Mammography
Risk assessment
Support vector machines
Mathematical operators
Textures

Keywords

  • Computer Aided Diagnosis
  • Local Ternary Patterns
  • Breast Cancer and Mammography

Cite this

Rampun, Andrik ; Morrow, PJ ; Scotney, BW ; Winder, RJ. / A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography. Unknown Host Publication. Vol. 71 2017. pp. 283-286
@inproceedings{2bda8e7619fd475c8e8110bce0b49d89,
title = "A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography",
abstract = "This paper presents a preliminary quantitative study for breast cancer risk assessment in mammography using mathematical operators called Local Ternary Patterns. The study covers three different mapping patterns namely uniform (‘u2’), nonuniform (‘ri’) and a combination of uniform and nonuniform (‘riu2’). These patterns are used as texture features to model the appearance of breast density within the fibroglandular disk area. Subsequently, the Support Vector Machine is employed as a classification approach and initial results suggest that the mapping pattern ‘riu2’ outperforms the others.",
keywords = "Computer Aided Diagnosis, Local Ternary Patterns, Breast Cancer and Mammography",
author = "Andrik Rampun and PJ Morrow and BW Scotney and RJ Winder",
year = "2017",
month = "5",
day = "21",
doi = "10.1007/978-3-319-59397-5_31",
language = "English",
isbn = "978-3-319-59396-8",
volume = "71",
pages = "283--286",
booktitle = "Unknown Host Publication",

}

Rampun, A, Morrow, PJ, Scotney, BW & Winder, RJ 2017, A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography. in Unknown Host Publication. vol. 71, pp. 283-286, International Conference on Innovation in Medicine and Healthcare 2017, 21/05/17. https://doi.org/10.1007/978-3-319-59397-5_31

A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography. / Rampun, Andrik; Morrow, PJ; Scotney, BW; Winder, RJ.

Unknown Host Publication. Vol. 71 2017. p. 283-286.

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

TY - GEN

T1 - A Quantitative Study of Local Ternary Patterns for Risk Assessment in Mammography

AU - Rampun, Andrik

AU - Morrow, PJ

AU - Scotney, BW

AU - Winder, RJ

PY - 2017/5/21

Y1 - 2017/5/21

N2 - This paper presents a preliminary quantitative study for breast cancer risk assessment in mammography using mathematical operators called Local Ternary Patterns. The study covers three different mapping patterns namely uniform (‘u2’), nonuniform (‘ri’) and a combination of uniform and nonuniform (‘riu2’). These patterns are used as texture features to model the appearance of breast density within the fibroglandular disk area. Subsequently, the Support Vector Machine is employed as a classification approach and initial results suggest that the mapping pattern ‘riu2’ outperforms the others.

AB - This paper presents a preliminary quantitative study for breast cancer risk assessment in mammography using mathematical operators called Local Ternary Patterns. The study covers three different mapping patterns namely uniform (‘u2’), nonuniform (‘ri’) and a combination of uniform and nonuniform (‘riu2’). These patterns are used as texture features to model the appearance of breast density within the fibroglandular disk area. Subsequently, the Support Vector Machine is employed as a classification approach and initial results suggest that the mapping pattern ‘riu2’ outperforms the others.

KW - Computer Aided Diagnosis

KW - Local Ternary Patterns

KW - Breast Cancer and Mammography

U2 - 10.1007/978-3-319-59397-5_31

DO - 10.1007/978-3-319-59397-5_31

M3 - Conference contribution

SN - 978-3-319-59396-8

VL - 71

SP - 283

EP - 286

BT - Unknown Host Publication

ER -