Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/19178
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Alharbi, Hajar Mohammedsaleh H | en |
dc.contributor.author | Falzon, Gregory | en |
dc.contributor.author | Kwan, Paul H | en |
dc.date.accessioned | 2016-06-21T16:42:00Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Proceedings of the Third IAPR Asian Conference on Pattern Recognition (ACPR 2015), p. 221-225 | en |
dc.identifier.isbn | 9781479961009 | en |
dc.identifier.uri | https://hdl.handle.net/1959.11/19178 | - |
dc.description.abstract | The visual similarity between normal breast tissues and abnormal lesions in digital mammogram images makes computer-aided diagnosis of breast cancer using automatically detected features a highly error-prone task. Our contribution in this paper is a novel feature reduction framework for selecting the most discriminative features that achieves both efficiency and classification accuracy. Our approach applies five individual feature-ranking methods including Fisher score, minimum redundancy-maximum relevance, relief-f, sequential forward feature selection, and genetic algorithm for sorting the extracted features and selecting the features with highest ranking to setup a classifier. Our method achieves an accuracy of 94.27% and a sensitivity of 98.36% with a specificity of 99.27% on a set of 1,100 mammogram patches taken from image retrieval in medical applications database using a neural network classifier, which competes with state-of-the-art classification accuracy 93.11%. Furthermore, we demonstrate that only 49 out of the 119 extracted features are sufficient to achieve the reported accuracy of normal vs. abnormal classification. | en |
dc.language | en | en |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en |
dc.relation.ispartof | Proceedings of the Third IAPR Asian Conference on Pattern Recognition (ACPR 2015) | en |
dc.title | A novel feature reduction framework for digital mammogram image classification | en |
dc.type | Conference Publication | en |
dc.relation.conference | ACPR 2015: 3rd Asian Conference on Pattern Recognition | en |
dc.identifier.doi | 10.1109/ACPR.2015.7486498 | en |
dc.subject.keywords | Pattern Recognition and Data Mining | en |
dc.subject.keywords | Image Processing | en |
dc.subject.keywords | Cancer Diagnosis | en |
local.contributor.firstname | Hajar Mohammedsaleh H | en |
local.contributor.firstname | Gregory | en |
local.contributor.firstname | Paul H | en |
local.subject.for2008 | 080106 Image Processing | en |
local.subject.for2008 | 111202 Cancer Diagnosis | en |
local.subject.for2008 | 080109 Pattern Recognition and Data Mining | en |
local.subject.seo2008 | 920102 Cancer and Related Disorders | en |
local.subject.seo2008 | 970108 Expanding Knowledge in the Information and Computing Sciences | en |
local.subject.seo2008 | 970111 Expanding Knowledge in the Medical and Health Sciences | en |
local.profile.school | School of Science and Technology | en |
local.profile.school | School of Science and Technology | en |
local.profile.email | halharbi@une.edu.au | en |
local.profile.email | gfalzon2@une.edu.au | en |
local.profile.email | wkwan2@une.edu.au | en |
local.output.category | E1 | en |
local.record.place | au | en |
local.record.institution | University of New England | en |
local.identifier.epublicationsrecord | une-20151118-094032 | en |
local.date.conference | 3rd - 6th November, 2015 | en |
local.conference.place | Kuala Lumpur, Malaysia | en |
local.publisher.place | Los Alamitos, United States of America | en |
local.format.startpage | 221 | en |
local.format.endpage | 225 | en |
local.peerreviewed | Yes | en |
local.contributor.lastname | Alharbi | en |
local.contributor.lastname | Falzon | en |
local.contributor.lastname | Kwan | en |
dc.identifier.staff | une-id:halharbi | en |
dc.identifier.staff | une-id:gfalzon2 | en |
dc.identifier.staff | une-id:wkwan2 | en |
local.profile.orcid | 0000-0002-1989-9357 | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.identifier.unepublicationid | une:19374 | en |
dc.identifier.academiclevel | Academic | en |
dc.identifier.academiclevel | Academic | en |
dc.identifier.academiclevel | Academic | en |
local.title.maintitle | A novel feature reduction framework for digital mammogram image classification | en |
local.output.categorydescription | E1 Refereed Scholarly Conference Publication | en |
local.conference.details | ACPR 2015: 3rd Asian Conference on Pattern Recognition, Kuala Lumpur, Malaysia, 3rd - 6th November, 2015 | en |
local.search.author | Alharbi, Hajar Mohammedsaleh H | en |
local.search.author | Falzon, Gregory | en |
local.search.author | Kwan, Paul H | en |
local.uneassociation | Unknown | en |
local.year.published | 2015 | en |
local.subject.for2020 | 460306 Image processing | en |
local.subject.for2020 | 321102 Cancer diagnosis | en |
local.subject.for2020 | 461199 Machine learning not elsewhere classified | en |
local.subject.seo2020 | 280115 Expanding knowledge in the information and computing sciences | en |
local.date.start | 2015-11-03 | - |
local.date.end | 2015-11-06 | - |
Appears in Collections: | Conference Publication |
Files in This Item:
File | Description | Size | Format |
---|
SCOPUSTM
Citations
3
checked on Oct 26, 2024
Page view(s)
1,578
checked on Apr 7, 2024
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.