A software tool for Microwave Tomography

Autores
Cervantes, Maria Jose; Gómez, Javier; Luparello, Diego; Morales, Martín; Fajardo, Jesus Ernesto; Galvan, Julian Marcelo; Caiafa, César Federico; Irastorza, Ramiro Miguel
Año de publicación
2023
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the recurrent application of proximal gradient algorithm. We learn a proximal map that works well with real images based on residual networks. Contraction of the resulting map is analyzed, and incoherence conditions are investigated that drive the convergence of the iterates. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled Fourier-spacedata and (b) superresolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block unrolled from an iterative algorithm yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.
Fil: Cervantes, Maria Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; Argentina
Fil: Gómez, Javier. Universidad Nacional Arturo Jauretche; Argentina
Fil: Luparello, Diego. Universidad Nacional Arturo Jauretche; Argentina
Fil: Morales, Martín. Universidad Nacional Arturo Jauretche; Argentina
Fil: Fajardo, Jesus Ernesto. University of Michigan; Estados Unidos
Fil: Galvan, Julian Marcelo. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Irastorza, Ramiro Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; Argentina
Proceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023
Buenos Aires
Argentina
Sociedad Argentina de Bioingeniería
Materia
microwave
tomography
software
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/246708
Acceder
id CONICETDig_1ec5c18e00a010c9aa9884975468a4be
oai_identifier_str oai:ri.conicet.gov.ar:11336/246708
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A software tool for Microwave TomographyCervantes, Maria JoseGómez, JavierLuparello, DiegoMorales, MartínFajardo, Jesus ErnestoGalvan, Julian MarceloCaiafa, César FedericoIrastorza, Ramiro Miguelmicrowavetomographysoftwarehttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the recurrent application of proximal gradient algorithm. We learn a proximal map that works well with real images based on residual networks. Contraction of the resulting map is analyzed, and incoherence conditions are investigated that drive the convergence of the iterates. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled Fourier-spacedata and (b) superresolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block unrolled from an iterative algorithm yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.Fil: Cervantes, Maria Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; ArgentinaFil: Gómez, Javier. Universidad Nacional Arturo Jauretche; ArgentinaFil: Luparello, Diego. Universidad Nacional Arturo Jauretche; ArgentinaFil: Morales, Martín. Universidad Nacional Arturo Jauretche; ArgentinaFil: Fajardo, Jesus Ernesto. University of Michigan; Estados UnidosFil: Galvan, Julian Marcelo. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Irastorza, Ramiro Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; ArgentinaProceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023Buenos AiresArgentinaSociedad Argentina de BioingenieríaSpringer Nature SwitzerlandBallina, Fernando EmilioArmentano, RicardoAcevedo, Rubén CarlosMeschino, Gustavo Javier2023info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectCongresoBookhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/246708A software tool for Microwave Tomography; Proceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023; Buenos Aires; Argentina; 2023; 1-129783031517228CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.springerprofessional.de/En/a-software-tool-for-microwave-tomography/27152812info:eu-repo/semantics/altIdentifier/url/https://www.springerprofessional.de/En/advances-in-bioengineering-and-clinical-engineering/27152706?tocPage=1Internacionalinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:53:39Zoai:ri.conicet.gov.ar:11336/246708instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:53:39.856CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A software tool for Microwave Tomography
title A software tool for Microwave Tomography
spellingShingle A software tool for Microwave Tomography
Cervantes, Maria Jose
microwave
tomography
software
title_short A software tool for Microwave Tomography
title_full A software tool for Microwave Tomography
title_fullStr A software tool for Microwave Tomography
title_full_unstemmed A software tool for Microwave Tomography
title_sort A software tool for Microwave Tomography
dc.creator.none.fl_str_mv Cervantes, Maria Jose
Gómez, Javier
Luparello, Diego
Morales, Martín
Fajardo, Jesus Ernesto
Galvan, Julian Marcelo
Caiafa, César Federico
Irastorza, Ramiro Miguel
author Cervantes, Maria Jose
author_facet Cervantes, Maria Jose
Gómez, Javier
Luparello, Diego
Morales, Martín
Fajardo, Jesus Ernesto
Galvan, Julian Marcelo
Caiafa, César Federico
Irastorza, Ramiro Miguel
author_role author
author2 Gómez, Javier
Luparello, Diego
Morales, Martín
Fajardo, Jesus Ernesto
Galvan, Julian Marcelo
Caiafa, César Federico
Irastorza, Ramiro Miguel
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Ballina, Fernando Emilio
Armentano, Ricardo
Acevedo, Rubén Carlos
Meschino, Gustavo Javier
dc.subject.none.fl_str_mv microwave
tomography
software
topic microwave
tomography
software
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the recurrent application of proximal gradient algorithm. We learn a proximal map that works well with real images based on residual networks. Contraction of the resulting map is analyzed, and incoherence conditions are investigated that drive the convergence of the iterates. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled Fourier-spacedata and (b) superresolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block unrolled from an iterative algorithm yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.
Fil: Cervantes, Maria Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; Argentina
Fil: Gómez, Javier. Universidad Nacional Arturo Jauretche; Argentina
Fil: Luparello, Diego. Universidad Nacional Arturo Jauretche; Argentina
Fil: Morales, Martín. Universidad Nacional Arturo Jauretche; Argentina
Fil: Fajardo, Jesus Ernesto. University of Michigan; Estados Unidos
Fil: Galvan, Julian Marcelo. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Irastorza, Ramiro Miguel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto de Física de Líquidos y Sistemas Biológicos. Universidad Nacional de La Plata. Facultad de Ciencias Exactas. Instituto de Física de Líquidos y Sistemas Biológicos; Argentina
Proceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023
Buenos Aires
Argentina
Sociedad Argentina de Bioingeniería
description Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training data faces severe challenges, including: (i) scarcity of training data; (ii) need for plausible reconstructions that are physically feasible; (iii) need for fast reconstruction, especially in real-time applications. We develop a successful system solving all these challenges, using as basic architecture the recurrent application of proximal gradient algorithm. We learn a proximal map that works well with real images based on residual networks. Contraction of the resulting map is analyzed, and incoherence conditions are investigated that drive the convergence of the iterates. Extensive experiments are carried out under different settings: (a) reconstructing abdominal MRI of pediatric patients from highly undersampled Fourier-spacedata and (b) superresolving natural face images. Our key findings include: 1. a recurrent ResNet with a single residual block unrolled from an iterative algorithm yields an effective proximal which accurately reveals MR image details. 2. Our architecture significantly outperforms conventional non-recurrent deep ResNets by 2dB SNR; it is also trained much more rapidly. 3. It outperforms state-of-the-art compressed-sensing Wavelet-based methods by 4dB SNR, with 100x speedups in reconstruction time.
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
Congreso
Book
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
status_str publishedVersion
format conferenceObject
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/246708
A software tool for Microwave Tomography; Proceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023; Buenos Aires; Argentina; 2023; 1-12
9783031517228
CONICET Digital
CONICET
url http://hdl.handle.net/11336/246708
identifier_str_mv A software tool for Microwave Tomography; Proceedings of the XXIV Argentinian Congress of Bioengineering. SABI 2023; Buenos Aires; Argentina; 2023; 1-12
9783031517228
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.springerprofessional.de/En/a-software-tool-for-microwave-tomography/27152812
info:eu-repo/semantics/altIdentifier/url/https://www.springerprofessional.de/En/advances-in-bioengineering-and-clinical-engineering/27152706?tocPage=1
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.coverage.none.fl_str_mv Internacional
dc.publisher.none.fl_str_mv Springer Nature Switzerland
publisher.none.fl_str_mv Springer Nature Switzerland
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613636964745216
score 13.070432

Publicaciones similares