Repository logo
 
Publication

A Two-Step Segmentation Method for Breast Ultrasound Masses Based on Multi-resolution Analysis

dc.contributor.authorRodrigues, Rafael
dc.contributor.authorBraz, Rui
dc.contributor.authorPereira, Manuela
dc.contributor.authorMoutinho, José
dc.contributor.authorPinheiro, Antonio M. G.
dc.date.accessioned2021-02-08T16:38:05Z
dc.date.available2021-02-08T16:38:05Z
dc.date.issued2015-02-28
dc.description.abstractBreast ultrasound images have several attractive properties that make them an interesting tool in breast cancer detection. However, their intrinsic high noise rate and low contrast turn mass detection and segmentation into a challenging task. In this article, a fully automated two-stage breast mass segmentation approach is proposed. In the initial stage, ultrasound images are segmented using support vector machine or discriminant analysis pixel classification with a multiresolution pixel descriptor. The features are extracted using non-linear diffusion, bandpass filtering and scale-variant mean curvature measures. A set of heuristic rules complement the initial segmentation stage, selecting the region of interest in a fully automated manner. In the second segmentation stage, refined segmentation of the area retrieved in the first stage is attempted, using two different techniques. The AdaBoost algorithm uses a descriptor based on scale-variant curvature measures and non-linear diffusion of the original image at lower scales, to improve the spatial accuracy of the ROI. Active contours use the segmentation results from the first stage as initial contours. Results for both proposed segmentation paths were promising, with normalized Dice similarity coefficients of 0.824 for AdaBoost and 0.813 for active contours. Recall rates were 79.6% for AdaBoost and 77.8% for active contours, whereas the precision rate was 89.3% for both methods.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1016/j.ultrasmedbio.2015.01.012pt_PT
dc.identifier.issn0301-5629
dc.identifier.urihttp://hdl.handle.net/10400.6/11103
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherElsevierpt_PT
dc.relation.publisherversionhttps://www.umbjournal.org/article/S0301-5629(15)00043-5/fulltextpt_PT
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/pt_PT
dc.subjectAlgorithmspt_PT
dc.subjectBreast Neoplasmspt_PT
dc.subjectComputer-assisted diagnosispt_PT
dc.subjectImage Interpretationpt_PT
dc.subjectImage Processingpt_PT
dc.subjectPattern Recognition, Automatedpt_PT
dc.subjectReproducibility of Resultspt_PT
dc.subjectUltrasonographypt_PT
dc.titleA Two-Step Segmentation Method for Breast Ultrasound Masses Based on Multi-resolution Analysispt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/PEst-OE%2FFIS%2FUI0524%2F2014/PT
oaire.citation.endPage1748pt_PT
oaire.citation.issue6pt_PT
oaire.citation.startPage1737pt_PT
oaire.citation.titleUltrasound in Medicine & Biologypt_PT
oaire.citation.volume41pt_PT
oaire.fundingStream5876
person.familyNameMendes Rodrigues
person.familyNamePereira
person.familyNameFonseca-Moutinho
person.familyNamePinheiro
person.givenNameJorge Rafael
person.givenNameManuela
person.givenNameJosé
person.givenNameAntonio
person.identifier.ciencia-idD112-43CA-98E0
person.identifier.ciencia-id0515-7E9C-B97F
person.identifier.ciencia-id2218-265E-17D2
person.identifier.orcid0000-0002-9481-9601
person.identifier.orcid0000-0002-8648-6464
person.identifier.orcid0000-0001-7157-3066
person.identifier.orcid0000-0002-5968-9901
person.identifier.ridB-2723-2012
person.identifier.scopus-author-id35248984200
person.identifier.scopus-author-id8420644500
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication16431ade-58b1-4db3-849b-718dd28e15bf
relation.isAuthorOfPublicationb89b2bbc-525d-4a6d-8a41-6ad7b81fa511
relation.isAuthorOfPublication55071707-afe1-4c4b-8191-54e4261dbd49
relation.isAuthorOfPublication94e6047a-198a-41bd-bd6c-b0f21708d8f9
relation.isAuthorOfPublication.latestForDiscovery94e6047a-198a-41bd-bd6c-b0f21708d8f9
relation.isProjectOfPublicationcef61258-e8c6-461c-a99f-52a6a570a258
relation.isProjectOfPublication.latestForDiscoverycef61258-e8c6-461c-a99f-52a6a570a258

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
UMB___A_Two_step_Segmentation_Method_for_Breast_Ultrasound_Masses_Based_on_Multi_resolution_Analysis.pdf
Size:
5.14 MB
Format:
Adobe Portable Document Format