Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network

[EN] Magnetic resonance imaging (MRI) is one of the most widely used tools for clinical diagnosis. Depending on the acquisition parameters, different image contrasts can be obtained, providing complementary information about the patient's anatomy and potential pathological findings. However...

Descripción completa

Detalles Bibliográficos
Autores: Morell-Ortega, Sergio|||0009-0001-7639-2915, Vivó, Roberto|||0000-0002-0751-4114, Rubio Navarro, Gregorio, DE LA IGLESIA VAYÁ, MARIA DE LOS DESAMPARADOS, Manjón Herrera, José Vicente|||0000-0001-6640-927X, Ruiz-Perez, Marina, Gadea, Marien, Aparici, Fernando, Thomas Tourdias, Mansencal, Boris, Coupé, Pierrick
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/226587
Acceso en línea:https://riunet.upv.es/handle/10251/226587
Access Level:acceso abierto
Palabra clave:MRI
Contrast synthesis
Deep learning
Semi-supervised learning
id ES_0b4f603e59fa2dff7ac0c5cb68fbeef4
oai_identifier_str oai:riunet.upv.es:10251/226587
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
title Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
spellingShingle Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
Morell-Ortega, Sergio|||0009-0001-7639-2915
MRI
Contrast synthesis
Deep learning
Semi-supervised learning
title_short Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
title_full Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
title_fullStr Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
title_full_unstemmed Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
title_sort Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D network
dc.creator.none.fl_str_mv Morell-Ortega, Sergio|||0009-0001-7639-2915
Vivó, Roberto|||0000-0002-0751-4114
Rubio Navarro, Gregorio
DE LA IGLESIA VAYÁ, MARIA DE LOS DESAMPARADOS
Manjón Herrera, José Vicente|||0000-0001-6640-927X
Ruiz-Perez, Marina
Gadea, Marien
Aparici, Fernando
Thomas Tourdias
Mansencal, Boris
Coupé, Pierrick
author Morell-Ortega, Sergio|||0009-0001-7639-2915
author_facet Morell-Ortega, Sergio|||0009-0001-7639-2915
Vivó, Roberto|||0000-0002-0751-4114
Rubio Navarro, Gregorio
DE LA IGLESIA VAYÁ, MARIA DE LOS DESAMPARADOS
Manjón Herrera, José Vicente|||0000-0001-6640-927X
Ruiz-Perez, Marina
Gadea, Marien
Aparici, Fernando
Thomas Tourdias
Mansencal, Boris
Coupé, Pierrick
author_role author
author2 Vivó, Roberto|||0000-0002-0751-4114
Rubio Navarro, Gregorio
DE LA IGLESIA VAYÁ, MARIA DE LOS DESAMPARADOS
Manjón Herrera, José Vicente|||0000-0001-6640-927X
Ruiz-Perez, Marina
Gadea, Marien
Aparici, Fernando
Thomas Tourdias
Mansencal, Boris
Coupé, Pierrick
author2_role author
author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Física Aplicada
Departamento de Sistemas Informáticos y Computación
Instituto Universitario de Tecnologías de la Información y Comunicaciones
Departamento de Matemática Aplicada
Instituto Universitario de Matemática Multidisciplinar
Instituto Universitario de Automática e Informática Industrial
Escuela Técnica Superior de Ingeniería Industrial
Escuela Técnica Superior de Ingeniería Informática
Agencia Estatal de Investigación
Universitat Politècnica de València
Agence Nationale de la Recherche, Francia
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv MRI
Contrast synthesis
Deep learning
Semi-supervised learning
topic MRI
Contrast synthesis
Deep learning
Semi-supervised learning
description [EN] Magnetic resonance imaging (MRI) is one of the most widely used tools for clinical diagnosis. Depending on the acquisition parameters, different image contrasts can be obtained, providing complementary information about the patient's anatomy and potential pathological findings. However, multiplying such acquisitions requires more time, additional resources, and increases patient discomfort. Consequently, not all image modalities are typically acquired. One solution to obtain the missing modalities is to use contrast synthesis methods. Most existing synthesis methods work with 2D slices due to memory limitations, which produces inconsistencies and artifacts when reconstructing the 3D volume. In this work, we present a 3D deep learning-based approach for synthesizing T2-weighted MR volumes from T1-weighted ones. To preserve anatomical details and enhance image quality, we propose a segmentation-oriented loss function combined with a frequency space information loss. To make the proposed method more robust and applicable to a wider range of image scenarios, we also incorporate a priori information in the form of a multi-atlas. Additionally, we employ a semi-supervised learning framework that improves the model's generalizability across diverse datasets, potentially improving its performance in clinical settings with varying patient demographics and imaging protocols. By integrating prior anatomical knowledge with frequency domain and segmentation loss functions, our approach outperforms state-of-the-art methods, particularly in segmentation tasks. The method demonstrates significant improvements, especially in challenging cases, compared with state-of-the-art approaches.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-08-26
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/226587
url https://riunet.upv.es/handle/10251/226587
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-152127OB-I00 DESARROLLO DE UN SOFTWARE DE ANALISIS DE IMAGEN DE RM CEREBRAL MULTIMODAL DE ULTRA-ALTA RESOLUCION PARA SU APLICACION A ENTORNOS CLINICOS
Agence Nationale de la Recherche, Francia https://doi.org/10.13039/501100001665 ANR-23-CE45-0020-01
Agence Nationale de la Recherche, Francia https://doi.org/10.13039/501100001665 ANR-23-IAHU- 0001
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Massachusetts Institute of Technology Press
publisher.none.fl_str_mv Massachusetts Institute of Technology Press
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869403213460930560
spelling Robust deep MRI contrast synthesis using a prior-based and task-oriented 3D networkMorell-Ortega, Sergio|||0009-0001-7639-2915Vivó, Roberto|||0000-0002-0751-4114Rubio Navarro, GregorioDE LA IGLESIA VAYÁ, MARIA DE LOS DESAMPARADOSManjón Herrera, José Vicente|||0000-0001-6640-927XRuiz-Perez, MarinaGadea, MarienAparici, FernandoThomas TourdiasMansencal, BorisCoupé, PierrickMRIContrast synthesisDeep learningSemi-supervised learning[EN] Magnetic resonance imaging (MRI) is one of the most widely used tools for clinical diagnosis. Depending on the acquisition parameters, different image contrasts can be obtained, providing complementary information about the patient's anatomy and potential pathological findings. However, multiplying such acquisitions requires more time, additional resources, and increases patient discomfort. Consequently, not all image modalities are typically acquired. One solution to obtain the missing modalities is to use contrast synthesis methods. Most existing synthesis methods work with 2D slices due to memory limitations, which produces inconsistencies and artifacts when reconstructing the 3D volume. In this work, we present a 3D deep learning-based approach for synthesizing T2-weighted MR volumes from T1-weighted ones. To preserve anatomical details and enhance image quality, we propose a segmentation-oriented loss function combined with a frequency space information loss. To make the proposed method more robust and applicable to a wider range of image scenarios, we also incorporate a priori information in the form of a multi-atlas. Additionally, we employ a semi-supervised learning framework that improves the model's generalizability across diverse datasets, potentially improving its performance in clinical settings with varying patient demographics and imaging protocols. By integrating prior anatomical knowledge with frequency domain and segmentation loss functions, our approach outperforms state-of-the-art methods, particularly in segmentation tasks. The method demonstrates significant improvements, especially in challenging cases, compared with state-of-the-art approaches.This work has been developed thanks to the project PID2023-152127OB-I00 of the Ministerio de Ciencia, Innovacion e Universidades of Spain. This work benefited from the support of the project HoliBrain of the French National Research Agency (ANR-23-CE45-0020-01). Moreover, this project is supported by the Precision and global vascular brain health institute funded by the France 2030 investment plan as part of the IHU3 initiative (ANR-23-IAHU- 0001). Finally, this study received financial support from the French government in the framework of the University of Bordeaux's France 2030 program/RRI IMPACT and the PEPR StratifyAging. We thank the support of ITACA (Institute of Information and Communication Technologies) at UPV (Universitat Politecnica de Valencia).Massachusetts Institute of Technology PressDepartamento de Física AplicadaDepartamento de Sistemas Informáticos y ComputaciónInstituto Universitario de Tecnologías de la Información y ComunicacionesDepartamento de Matemática AplicadaInstituto Universitario de Matemática MultidisciplinarInstituto Universitario de Automática e Informática IndustrialEscuela Técnica Superior de Ingeniería IndustrialEscuela Técnica Superior de Ingeniería InformáticaAgencia Estatal de InvestigaciónUniversitat Politècnica de ValènciaAgence Nationale de la Recherche, FranciaRepositorio Institucional de la Universitat Politècnica de València Riunet20252025-08-26journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://riunet.upv.es/handle/10251/226587reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-152127OB-I00 DESARROLLO DE UN SOFTWARE DE ANALISIS DE IMAGEN DE RM CEREBRAL MULTIMODAL DE ULTRA-ALTA RESOLUCION PARA SU APLICACION A ENTORNOS CLINICOSAgence Nationale de la Recherche, Francia https://doi.org/10.13039/501100001665 ANR-23-CE45-0020-01Agence Nationale de la Recherche, Francia https://doi.org/10.13039/501100001665 ANR-23-IAHU- 0001open accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento (by)http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/2265872026-06-13T07:49:27Z
score 15,812455

Similares en LA Referencia