Export Ready — 

Breast skin-line detection using dynamic programming

Bibliographic Details
Main Author: Silva, C. A.
Publication Date: 2011
Other Authors: Lima, C. G., Correia, J. H.
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/1822/15670
Summary: In this paper, we present a novel method to extract the breast skin-line based on dynamic programming. Skin-line extraction is an important preprocessing step in CAD systems; however, it is a challenging problem due to the presence of noise, underexposed regions, which results in a low contrast area near the skin-air interface, and artifacts such as labels. Our proposal utilizes the stroma edge to constrain searching for the border. In order to cope with noise, we consider several candidate points for the border interface which are obtained by the Laplace operator applied in pre-defined directions in the mammogram. The breast contour is obtained from the candidate points using a dynamic programming algorithm. This utilizes a criterion of optimality to obtain the optimum contour by minimization of a cost function. The method was evaluated using 82 mammograms whose contour were manually extracted by a radiologist from the mini- MIAS database. The Polyline Distance Measure was evaluated for each contour selected with the proposed method, obtaining a mean error of 2.05 pixels and a standard deviation of 0.80.
id RCAP_b98d2bd68e47f17a91e1845cd9c23682
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/15670
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Breast skin-line detection using dynamic programmingMammographyBreast skin-lineDynamic programmingScience & TechnologyIn this paper, we present a novel method to extract the breast skin-line based on dynamic programming. Skin-line extraction is an important preprocessing step in CAD systems; however, it is a challenging problem due to the presence of noise, underexposed regions, which results in a low contrast area near the skin-air interface, and artifacts such as labels. Our proposal utilizes the stroma edge to constrain searching for the border. In order to cope with noise, we consider several candidate points for the border interface which are obtained by the Laplace operator applied in pre-defined directions in the mammogram. The breast contour is obtained from the candidate points using a dynamic programming algorithm. This utilizes a criterion of optimality to obtain the optimum contour by minimization of a cost function. The method was evaluated using 82 mammograms whose contour were manually extracted by a radiologist from the mini- MIAS database. The Polyline Distance Measure was evaluated for each contour selected with the proposed method, obtaining a mean error of 2.05 pixels and a standard deviation of 0.80.Fundação para a Ciência e a Tecnologia (FCT)IEEEUniversidade do MinhoSilva, C. A.Lima, C. G.Correia, J. H.2011-092011-09-01T00:00:00Zconference paperinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/1822/15670eng97814244412111557-170X10.1109/IEMBS.2011.6091916http://dx.doi.org/10.1109/IEMBS.2011.6091916info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-11T04:27:34Zoai:repositorium.sdum.uminho.pt:1822/15670Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T14:48:47.896854Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Breast skin-line detection using dynamic programming
title Breast skin-line detection using dynamic programming
spellingShingle Breast skin-line detection using dynamic programming
Silva, C. A.
Mammography
Breast skin-line
Dynamic programming
Science & Technology
title_short Breast skin-line detection using dynamic programming
title_full Breast skin-line detection using dynamic programming
title_fullStr Breast skin-line detection using dynamic programming
title_full_unstemmed Breast skin-line detection using dynamic programming
title_sort Breast skin-line detection using dynamic programming
author Silva, C. A.
author_facet Silva, C. A.
Lima, C. G.
Correia, J. H.
author_role author
author2 Lima, C. G.
Correia, J. H.
author2_role author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Silva, C. A.
Lima, C. G.
Correia, J. H.
dc.subject.por.fl_str_mv Mammography
Breast skin-line
Dynamic programming
Science & Technology
topic Mammography
Breast skin-line
Dynamic programming
Science & Technology
description In this paper, we present a novel method to extract the breast skin-line based on dynamic programming. Skin-line extraction is an important preprocessing step in CAD systems; however, it is a challenging problem due to the presence of noise, underexposed regions, which results in a low contrast area near the skin-air interface, and artifacts such as labels. Our proposal utilizes the stroma edge to constrain searching for the border. In order to cope with noise, we consider several candidate points for the border interface which are obtained by the Laplace operator applied in pre-defined directions in the mammogram. The breast contour is obtained from the candidate points using a dynamic programming algorithm. This utilizes a criterion of optimality to obtain the optimum contour by minimization of a cost function. The method was evaluated using 82 mammograms whose contour were manually extracted by a radiologist from the mini- MIAS database. The Polyline Distance Measure was evaluated for each contour selected with the proposed method, obtaining a mean error of 2.05 pixels and a standard deviation of 0.80.
publishDate 2011
dc.date.none.fl_str_mv 2011-09
2011-09-01T00:00:00Z
dc.type.driver.fl_str_mv conference paper
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/1822/15670
url http://hdl.handle.net/1822/15670
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 9781424441211
1557-170X
10.1109/IEMBS.2011.6091916
http://dx.doi.org/10.1109/IEMBS.2011.6091916
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833594905375539200