Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1117/12.2513140 http://hdl.handle.net/11449/187829 |
Resumo: | Noise is an intrinsic property of every imaging system. For imaging systems using ionizing radiation, such as digital breast tomosynthesis (DBT) or digital mammography (DM), we strive to ensure that x-ray quantum noise is the limiting noise source in images, while using the lowest radiation dose possible to achieve clinically satisfactory images. Therefore, new computer methods are being sought to help reduce the dose of these systems. In the case of DBT, this can be achieved when solving the inverse problem of tomographic reconstruction. In this work, we propose to use a Non-Local Gaussian Markov Random Field (NLGMRF) model to represent a priori knowledge in a Bayesian (Maximum a Posteriori - MAP) reconstruction approach for DBT. The main advantage of the Non-Local Markov Random Field models is that they explicitly consider two important constraints to regularize the solution of this inverse problem - smoothing and redundancy. To evaluate this new method in DBT, a number of experiments were performed to compare these methods to existing reconstruction techniques. Comparable or superior results were achieved when compared with methods in the DBT reconstruction literature in terms of structural similarity index (SSIM), artifact spread function (ASF) and visual analysis, demonstrating that the NLGMRF model is suitable to regularize the MAP solution in DBT reconstruction. |
id |
UNSP_cee837a050b7823c62c6267dea5b1e0d |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/187829 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori modelBayesian approachDigital breast tomosynthesisNoise reductionNon local markov random fieldTomographic reconstructionNoise is an intrinsic property of every imaging system. For imaging systems using ionizing radiation, such as digital breast tomosynthesis (DBT) or digital mammography (DM), we strive to ensure that x-ray quantum noise is the limiting noise source in images, while using the lowest radiation dose possible to achieve clinically satisfactory images. Therefore, new computer methods are being sought to help reduce the dose of these systems. In the case of DBT, this can be achieved when solving the inverse problem of tomographic reconstruction. In this work, we propose to use a Non-Local Gaussian Markov Random Field (NLGMRF) model to represent a priori knowledge in a Bayesian (Maximum a Posteriori - MAP) reconstruction approach for DBT. The main advantage of the Non-Local Markov Random Field models is that they explicitly consider two important constraints to regularize the solution of this inverse problem - smoothing and redundancy. To evaluate this new method in DBT, a number of experiments were performed to compare these methods to existing reconstruction techniques. Comparable or superior results were achieved when compared with methods in the DBT reconstruction literature in terms of structural similarity index (SSIM), artifact spread function (ASF) and visual analysis, demonstrating that the NLGMRF model is suitable to regularize the MAP solution in DBT reconstruction.Sao Paulo State University (Unesp) Institute of Geosciences and Exact Sciences, Av. 24A, 1515University of Sao Paulo Sao Carlos School of Engineering, Av. Trabalhador Sao Carlense, 400University of Pennsylvania Hospital of the University of Pennsylvania Department of Radiology, 3400 Spruce Street, PhiladelphiaSao Paulo State University (Unesp) Institute of Geosciences and Exact Sciences, Av. 24A, 1515Universidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Hospital of the University of PennsylvaniaSalvadeo, Denis H. P. [UNESP]Vimieiro, Rodrigo B.Vieira, Marcelo A. C.Maidment, Andrew D. A.2019-10-06T15:48:29Z2019-10-06T15:48:29Z2019-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1117/12.2513140Progress in Biomedical Optics and Imaging - Proceedings of SPIE, v. 10948.1605-7422http://hdl.handle.net/11449/18782910.1117/12.25131402-s2.0-85068386811Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProgress in Biomedical Optics and Imaging - Proceedings of SPIEinfo:eu-repo/semantics/openAccess2021-10-22T21:10:11Zoai:repositorio.unesp.br:11449/187829Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T15:02:23.842743Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
title |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
spellingShingle |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model Salvadeo, Denis H. P. [UNESP] Bayesian approach Digital breast tomosynthesis Noise reduction Non local markov random field Tomographic reconstruction |
title_short |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
title_full |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
title_fullStr |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
title_full_unstemmed |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
title_sort |
Bayesian reconstruction for digital breast tomosynthesis using a non-local Gaussian Markov random field a priori model |
author |
Salvadeo, Denis H. P. [UNESP] |
author_facet |
Salvadeo, Denis H. P. [UNESP] Vimieiro, Rodrigo B. Vieira, Marcelo A. C. Maidment, Andrew D. A. |
author_role |
author |
author2 |
Vimieiro, Rodrigo B. Vieira, Marcelo A. C. Maidment, Andrew D. A. |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade de São Paulo (USP) Hospital of the University of Pennsylvania |
dc.contributor.author.fl_str_mv |
Salvadeo, Denis H. P. [UNESP] Vimieiro, Rodrigo B. Vieira, Marcelo A. C. Maidment, Andrew D. A. |
dc.subject.por.fl_str_mv |
Bayesian approach Digital breast tomosynthesis Noise reduction Non local markov random field Tomographic reconstruction |
topic |
Bayesian approach Digital breast tomosynthesis Noise reduction Non local markov random field Tomographic reconstruction |
description |
Noise is an intrinsic property of every imaging system. For imaging systems using ionizing radiation, such as digital breast tomosynthesis (DBT) or digital mammography (DM), we strive to ensure that x-ray quantum noise is the limiting noise source in images, while using the lowest radiation dose possible to achieve clinically satisfactory images. Therefore, new computer methods are being sought to help reduce the dose of these systems. In the case of DBT, this can be achieved when solving the inverse problem of tomographic reconstruction. In this work, we propose to use a Non-Local Gaussian Markov Random Field (NLGMRF) model to represent a priori knowledge in a Bayesian (Maximum a Posteriori - MAP) reconstruction approach for DBT. The main advantage of the Non-Local Markov Random Field models is that they explicitly consider two important constraints to regularize the solution of this inverse problem - smoothing and redundancy. To evaluate this new method in DBT, a number of experiments were performed to compare these methods to existing reconstruction techniques. Comparable or superior results were achieved when compared with methods in the DBT reconstruction literature in terms of structural similarity index (SSIM), artifact spread function (ASF) and visual analysis, demonstrating that the NLGMRF model is suitable to regularize the MAP solution in DBT reconstruction. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-06T15:48:29Z 2019-10-06T15:48:29Z 2019-01-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1117/12.2513140 Progress in Biomedical Optics and Imaging - Proceedings of SPIE, v. 10948. 1605-7422 http://hdl.handle.net/11449/187829 10.1117/12.2513140 2-s2.0-85068386811 |
url |
http://dx.doi.org/10.1117/12.2513140 http://hdl.handle.net/11449/187829 |
identifier_str_mv |
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, v. 10948. 1605-7422 10.1117/12.2513140 2-s2.0-85068386811 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Progress in Biomedical Optics and Imaging - Proceedings of SPIE |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128450143191040 |