End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA

Simple item page
dc.catalogadorgjm
dc.contributor.authorQi, Haikun
dc.contributor.authorHajhosseiny, Reza
dc.contributor.authorCruz, Gastao
dc.contributor.authorKuestner, Thomas
dc.contributor.authorKunze, Karl
dc.contributor.authorNeji, Radhouene
dc.contributor.authorBotnar, René Michael
dc.contributor.authorPrieto Vásquez, Claudia
dc.date.accessioned2023-05-19T20:46:45Z
dc.date.available2023-05-19T20:46:45Z
dc.date.issued2021
dc.description.abstractPurpose: To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA).
dc.description.abstractMethods: A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (similar to 22x) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions.
dc.description.abstractResults: The acquisition time for ninefold accelerated CMRA was similar to 2.5 min. The reconstruction time was similar to 22 s for the proposed MoCo-MoDL and similar to 35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 +/- 3.00 vs. 26.71 +/- 2.79; P < .05) and structural similarity (0.78 +/- 0.06 vs. 0.75 +/- 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL.
dc.description.abstractConclusion: An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow.
dc.fechaingreso.objetodigital2023-07-14
dc.fuente.origenORCID
dc.identifier.doi10.1002/mrm.28851
dc.identifier.eissn1522-2594
dc.identifier.issn0740-3194
dc.identifier.pubmedidPMID: 34096095
dc.identifier.urihttps://doi.org/10.1002/mrm.28851
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/69869
dc.information.autorucEscuela de Ingeniería; Botnar, René Michael; 0000-0002-9447-4367; 1015313
dc.information.autorucEscuela de Ingeniería; Prieto Vásquez, Claudia; 0000-0003-4602-2523; 14195
dc.issue.numero4
dc.language.isoen
dc.nota.accesoContenido completo
dc.pagina.final1996
dc.pagina.inicio1983
dc.revistaMagnetic Resonance in Medicine
dc.rightsacceso abierto
dc.subjectCoronary MRAes_ES
dc.subjectDeep learning nonrigid motion correctiones_ES
dc.subjectDeep learning reconstructiones_ES
dc.subjectFree-breathing cardiac MRIes_ES
dc.subject.ddc620
dc.subject.deweyIngenieríaes_ES
dc.titleEnd-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRAes_ES
dc.typeartículo
dc.volumen86
sipa.codpersvinculados1015313
sipa.codpersvinculados14195
sipa.indexPubmed
sipa.trazabilidadORCID;14-07-2023
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
end_to_end_deep_learning.pdf
Size:
1.6 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas