Evaluation of mammogram co-registration using mutual information

Autores
Foglino, Emiliano; Nores, María Laura; Rulloni, Valeria
Año de publicación
2017
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Fil: Foglino, Emiliano. Hospital Córdoba; Argentina.
Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.
Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.
Digital image processing is an area of growing interest. In this context, special importance has the co-registration of two images of the same place but recorded at different times. This is very useful in medicine; for example, radiologists routinely use several mammographic views along with previous mammograms for detecting and monitoring breast lesions. For a good comparison, images must coincide in space and conditions. In this work, it was addressed the problem of mammogram co-registration. Once the region of interest is automatically detected, the nipple locations are identified and matched. Then, the rotation and scale that maximize the Mutual Information between both images are selected. This is made in two stages: first, the maximum is searched through all values for rotation and scale in a grid. Then, the search is restricted to the region limited by the points in the grid nearest to the initial estimate. This method was applied to simulated and real data, showing a good performance. Once the correspondence between current and previous mammograms is established, the difference image could be calculated and an interval change analysis could be performed. Thus, this work contributes to increase and interpret the information that can be extracted from medical images.
https://drive.google.com/file/d/0B8bkSevnWT2MU1pONG85dnpoZVYyZ183dWJVWUlRVjhsbEhV/view
Fil: Foglino, Emiliano. Hospital Córdoba; Argentina.
Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.
Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.
Matemática Aplicada
Materia
Biomedical image processing
Breast screening
Entropy
Image registration
Mammography
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Repositorio
Repositorio Digital Universitario (UNC)
Institución
Universidad Nacional de Córdoba
OAI Identificador
oai:rdu.unc.edu.ar:11086/556793
Acceder
id RDUUNC_d3ee284c82a795be1d93b1a338273fb5
oai_identifier_str oai:rdu.unc.edu.ar:11086/556793
network_acronym_str RDUUNC
repository_id_str 2572
network_name_str Repositorio Digital Universitario (UNC)
spelling Evaluation of mammogram co-registration using mutual informationFoglino, EmilianoNores, María LauraRulloni, ValeriaBiomedical image processingBreast screeningEntropyImage registrationMammographyFil: Foglino, Emiliano. Hospital Córdoba; Argentina.Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.Digital image processing is an area of growing interest. In this context, special importance has the co-registration of two images of the same place but recorded at different times. This is very useful in medicine; for example, radiologists routinely use several mammographic views along with previous mammograms for detecting and monitoring breast lesions. For a good comparison, images must coincide in space and conditions. In this work, it was addressed the problem of mammogram co-registration. Once the region of interest is automatically detected, the nipple locations are identified and matched. Then, the rotation and scale that maximize the Mutual Information between both images are selected. This is made in two stages: first, the maximum is searched through all values for rotation and scale in a grid. Then, the search is restricted to the region limited by the points in the grid nearest to the initial estimate. This method was applied to simulated and real data, showing a good performance. Once the correspondence between current and previous mammograms is established, the difference image could be calculated and an interval change analysis could be performed. Thus, this work contributes to increase and interpret the information that can be extracted from medical images.https://drive.google.com/file/d/0B8bkSevnWT2MU1pONG85dnpoZVYyZ183dWJVWUlRVjhsbEhV/viewFil: Foglino, Emiliano. Hospital Córdoba; Argentina.Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.Matemática Aplicada2017info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf978-987-572-272-9http://hdl.handle.net/11086/556793enginfo:eu-repo/semantics/openAccessreponame:Repositorio Digital Universitario (UNC)instname:Universidad Nacional de Córdobainstacron:UNC2025-09-29T13:42:53Zoai:rdu.unc.edu.ar:11086/556793Institucionalhttps://rdu.unc.edu.ar/Universidad públicaNo correspondehttp://rdu.unc.edu.ar/oai/snrdoca.unc@gmail.comArgentinaNo correspondeNo correspondeNo correspondeopendoar:25722025-09-29 13:42:54.127Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdobafalse
dc.title.none.fl_str_mv Evaluation of mammogram co-registration using mutual information
title Evaluation of mammogram co-registration using mutual information
spellingShingle Evaluation of mammogram co-registration using mutual information
Foglino, Emiliano
Biomedical image processing
Breast screening
Entropy
Image registration
Mammography
title_short Evaluation of mammogram co-registration using mutual information
title_full Evaluation of mammogram co-registration using mutual information
title_fullStr Evaluation of mammogram co-registration using mutual information
title_full_unstemmed Evaluation of mammogram co-registration using mutual information
title_sort Evaluation of mammogram co-registration using mutual information
dc.creator.none.fl_str_mv Foglino, Emiliano
Nores, María Laura
Rulloni, Valeria
author Foglino, Emiliano
author_facet Foglino, Emiliano
Nores, María Laura
Rulloni, Valeria
author_role author
author2 Nores, María Laura
Rulloni, Valeria
author2_role author
author
dc.subject.none.fl_str_mv Biomedical image processing
Breast screening
Entropy
Image registration
Mammography
topic Biomedical image processing
Breast screening
Entropy
Image registration
Mammography
dc.description.none.fl_txt_mv Fil: Foglino, Emiliano. Hospital Córdoba; Argentina.
Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.
Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.
Digital image processing is an area of growing interest. In this context, special importance has the co-registration of two images of the same place but recorded at different times. This is very useful in medicine; for example, radiologists routinely use several mammographic views along with previous mammograms for detecting and monitoring breast lesions. For a good comparison, images must coincide in space and conditions. In this work, it was addressed the problem of mammogram co-registration. Once the region of interest is automatically detected, the nipple locations are identified and matched. Then, the rotation and scale that maximize the Mutual Information between both images are selected. This is made in two stages: first, the maximum is searched through all values for rotation and scale in a grid. Then, the search is restricted to the region limited by the points in the grid nearest to the initial estimate. This method was applied to simulated and real data, showing a good performance. Once the correspondence between current and previous mammograms is established, the difference image could be calculated and an interval change analysis could be performed. Thus, this work contributes to increase and interpret the information that can be extracted from medical images.
https://drive.google.com/file/d/0B8bkSevnWT2MU1pONG85dnpoZVYyZ183dWJVWUlRVjhsbEhV/view
Fil: Foglino, Emiliano. Hospital Córdoba; Argentina.
Fil: Nores, María Laura. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía, Física y Computación. CIEM; Argentina.
Fil: Rulloni, Valeria. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales; Argentina.
Matemática Aplicada
description Fil: Foglino, Emiliano. Hospital Córdoba; Argentina.
publishDate 2017
dc.date.none.fl_str_mv 2017
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv 978-987-572-272-9
http://hdl.handle.net/11086/556793
identifier_str_mv 978-987-572-272-9
url http://hdl.handle.net/11086/556793
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositorio Digital Universitario (UNC)
instname:Universidad Nacional de Córdoba
instacron:UNC
reponame_str Repositorio Digital Universitario (UNC)
collection Repositorio Digital Universitario (UNC)
instname_str Universidad Nacional de Córdoba
instacron_str UNC
institution UNC
repository.name.fl_str_mv Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdoba
repository.mail.fl_str_mv oca.unc@gmail.com
_version_ 1844618939745697792
score 13.070432

Publicaciones similares