Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute

Simple item page
dc.contributor.authorKüstner T.
dc.contributor.authorMunoz C.
dc.contributor.authorPsenicny A.
dc.contributor.authorBustin A.
dc.contributor.authorFuin N.
dc.contributor.authorQi H.
dc.contributor.authorNeji R.
dc.contributor.authorKunze K.
dc.contributor.authorHajhosseiny R.
dc.contributor.authorPrieto C.
dc.contributor.authorBotnar R.
dc.contributor.authorKüstner T.
dc.contributor.authorBustin A.
dc.contributor.authorNeji R.
dc.contributor.authorKunze K.
dc.contributor.authorPrieto C.
dc.contributor.authorBotnar R.
dc.date.accessioned2024-01-10T14:22:44Z
dc.date.available2024-01-10T14:22:44Z
dc.date.issued2021
dc.description.abstract© 2021 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in MedicinePurpose: To develop and evaluate a novel and generalizable super-resolution (SR) deep-learning framework for motion-compensated isotropic 3D coronary MR angiography (CMRA), which allows free-breathing acquisitions in less than a minute. Methods: Undersampled motion-corrected reconstructions have enabled free-breathing isotropic 3D CMRA in ~5-10 min acquisition times. In this work, we propose a deep-learning–based SR framework, combined with non-rigid respiratory motion compensation, to shorten the acquisition time to less than 1 min. A generative adversarial network (GAN) is proposed consisting of two cascaded Enhanced Deep Residual Network generator, a trainable discriminator, and a perceptual loss network. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution (HR) isotropic CMRA (0.9 mm3 or 1.2 mm3) from a low-resolution (LR) anisotropic CMRA (0.9 × 3.6 × 3.6 mm3 or 1.2 × 4.8 × 4.8 mm3). The impact and generalization of the proposed SRGAN approach to different input resolutions and operation on image and patch-level is investigated. SRGAN was evaluated on a retrospective downsampled cohort of 50 patients and on 16 prospective patients that were scanned with LR-CMRA in ~50 s under free-breathing. Vessel sharpness and length of the coronary arteries from the SR-CMRA is compared against the HR-CMRA. Results: SR-CMRA showed statistically significant (P <.001) improved vessel sharpness 34.1% ± 12.3% and length 41.5% ± 8.1% compared with LR-CMRA. Good generalization to input resolution and image/patch-level processing was found. SR-CMRA enabled recovery of coronary stenosis similar to HR-CMRA with comparable qualitative performance. Conclusion: The proposed SR-CMRA provides a 16-fold increase in spatial resolution with comparable image quality to HR-CMRA while reducing the predictable scan time to <1 min.
dc.description.funderCardiovascular Health Technology Cooperative
dc.description.funderHTC
dc.description.funderWellcome EPSRC Centre for Medical Engineering
dc.description.funderKing’s College London
dc.description.funderWellcome Trust
dc.description.funderKing’s College Hospital NHS Foundation Trust
dc.description.funderBiomedical Research Centre
dc.description.funderEPSRC
dc.description.funderNational Institute for Health Research
dc.description.funderBHF
dc.description.funderDepartment of Health
dc.description.funderFONDECYT
dc.fechaingreso.objetodigital2024-04-09
dc.fuente.origenScopus
dc.identifier.doi10.1002/mrm.28911
dc.identifier.eissn15222594
dc.identifier.issn15222594 07403194
dc.identifier.pubmedidMEDLINE:34240753
dc.identifier.scopusidSCOPUS_ID:85109373143
dc.identifier.urihttps://doi.org/10.1002/mrm.28911
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/79993
dc.identifier.wosidWOS:000671216800001
dc.information.autorucFacultad de Ingeniería; Prieto Vasquez, Claudia Del Carmen; S/I; 14195
dc.language.isoen
dc.nota.accesocontenido completo
dc.publisherJohn Wiley and Sons Inc
dc.revistaMagnetic Resonance in Medicine
dc.rightsacceso abierto
dc.subject3D whole-heart
dc.subjectcoronary MR angiography
dc.subjectdeep learning
dc.subjectsuper resolution
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleDeep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute
dc.typeartículo
sipa.codpersvinculados14195
sipa.indexWos
sipa.indexScopus
sipa.trazabilidadCarga SIPA;09-01-2024
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Deep-learning based super-resolution for 3D isotropic coronary MR angiography in less than a minute.pdf
Size:
2.27 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas