A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis

Simple item page
dc.contributor.authorMachado, Ines
dc.contributor.authorPuyol-Anton, Esther
dc.contributor.authorHammernik, Kerstin
dc.contributor.authorCruz, Gastao
dc.contributor.authorUgurlu, Devran
dc.contributor.authorOlakorede, Ihsane
dc.contributor.authorOksuz, Ilkay
dc.contributor.authorRuijsink, Bram
dc.contributor.authorCastelo-Branco, Miguel
dc.contributor.authorYoung, Alistair
dc.contributor.authorPrieto, Claudia
dc.contributor.authorSchnabel, Julia
dc.contributor.authorKing, Andrew
dc.date.accessioned2025-01-20T17:07:01Z
dc.date.available2025-01-20T17:07:01Z
dc.date.issued2024
dc.description.abstractCine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.
dc.description.funderEngineering and Physical Sciences Research Council
dc.fuente.origenWOS
dc.identifier.doi10.1109/TBME.2023.3321431
dc.identifier.eissn1558-2531
dc.identifier.issn0018-9294
dc.identifier.urihttps://doi.org/10.1109/TBME.2023.3321431
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/90830
dc.identifier.wosidWOS:001178132900002
dc.issue.numero3
dc.language.isoen
dc.pagina.final865
dc.pagina.inicio855
dc.revistaIeee transactions on biomedical engineering
dc.rightsacceso restringido
dc.subjectCardiac MRI
dc.subjectdeep learning
dc.subjectfast reconstruction
dc.subjectquality assessment
dc.subjectsegmentation
dc.subjectUK BioBank
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleA Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis
dc.typeartículo
dc.volumen71
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas