Breast skin-line detection using dynamic programming
| Main Author: | |
|---|---|
| Publication Date: | 2011 |
| Other Authors: | , |
| 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 |