Unsupervised reconstruction of accelerated cardiac cine MRI using neural fields

Simple item page
dc.article.number109467
dc.catalogadoraba
dc.contributor.authorCatalán, T.
dc.contributor.authorCourdurier Bettancourt, Matías Alejandro
dc.contributor.authorOsses, A.
dc.contributor.authorFotaki, A.
dc.contributor.authorBotnar, René Michael
dc.contributor.authorSahli Costabal, F.
dc.contributor.authorPrieto, C.
dc.date.accessioned2025-04-01T13:21:36Z
dc.date.available2025-04-01T13:21:36Z
dc.date.issued2025
dc.description.abstractBackground: Cardiac cine MRI is the gold standard for cardiac functional assessment, but the inherently slow acquisition process creates the necessity of reconstruction approaches for accelerated undersampled acquisitions. Several regularization approaches that exploit spatial–temporal redundancy have been proposed to reconstruct undersampled cardiac cine MRI. More recently, methods based on supervised deep learning have been also proposed to further accelerate acquisition and reconstruction. However, these techniques rely on usually large dataset for training, which are not always available and might introduce biases. Methods: In this work we propose NF-cMRI, an unsupervised approach based on implicit neural field representations for cardiac cine MRI. We evaluate our method in in-vivo undersampled golden-angle radial multi-coil acquisitions for undersampling factors of 13x, 17x and 26x. Results: The proposed method achieves excellent scores in sharpness and robustness to artifacts and comparable or improved spatial–temporal depiction than state-of-the-art conventional and unsupervised deep learning reconstruction techniques. Conclusions: We have demonstrated NF-cMRI potential for cardiac cine MRI reconstruction with highly undersampled data.
dc.description.funderMillennium Nucleus for Applied Control and Inverse Problems ACIP; Folio: NCN19_161
dc.description.funderMillennium Institute for Intelligent Healthcare Engineering iHEALTH; Folio: ICN2021_004
dc.description.funderANID Basal; folio: FB210005
dc.description.funderANID/FONDECYT; Folio: 1210637
dc.description.funderANID Basal; Folio: FB210017
dc.description.funderANID/FONDECYT; Folio: 11220816
dc.format.extent10 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1016/j.compbiomed.2024.109467
dc.identifier.eissn1879-0534
dc.identifier.issn0010-4825
dc.identifier.scopusid2-s2.0-85211984504
dc.identifier.urihttps://doi.org/10.1016/j.compbiomed.2024.109467
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/103072
dc.information.autorucFacultad de Matemáticas; Courdurier Bettancourt, Matías Alejandro; 0000-0002-2161-0356; 1007892
dc.information.autorucInstituto de Ingeniería Biológica y Médica; Botnar, René Michael; 0000-0003-2811-2509; 1015313
dc.language.isoen
dc.nota.accesocontenido parcial
dc.revistaComputers in Biology and Medicine
dc.rightsacceso restringido
dc.subjectCardiac cine MRI
dc.subjectDeep learning
dc.subjectUnsupervised MRI reconstruction
dc.subjectNeural fields
dc.subject.ddc610
dc.subject.deweyMedicina y saludes_ES
dc.titleUnsupervised reconstruction of accelerated cardiac cine MRI using neural fields
dc.typeartículo
dc.volumen185
sipa.codpersvinculados1007892
sipa.codpersvinculados1015313
sipa.trazabilidadORCID;2025-03-03
Files
Collections
Artículos de revistas