Self-supervised learning-based diffeomorphic non-rigid motion estimation for fast motion-compensated coronary MR angiography

Simple item page
dc.contributor.authorMunoz, Camila
dc.contributor.authorQi, Haikun
dc.contributor.authorCruz, Gastao
dc.contributor.authorKuestner, Thomas
dc.contributor.authorBotnar, Rene M.
dc.contributor.authorPrieto, Claudia
dc.date.accessioned2024-01-10T13:44:56Z
dc.date.available2024-01-10T13:44:56Z
dc.date.issued2022
dc.description.abstractPurpose: To accelerate non-rigid motion corrected coronary MR angiography (CMRA) reconstruction by developing a deep learning based non-rigid motion estimation network and combining this with an efficient implementation of the undersampled motion corrected reconstruction.
dc.description.abstractMethods: Undersampled and respiratory motion corrected CMRA with overall short scans of 5 to 10 min have been recently proposed. However, image reconstruction with this approach remains lengthy, since it relies on several non-rigid image registrations to estimate the respiratory motion and on a subsequent iterative optimization to correct for motion during the undersampled reconstruction. Here we introduce a self-supervised diffeomorphic non-rigid respiratory motion estimation network, DiRespME-net, to speed up respiratory motion estimation. We couple this with an efficient GPU-based implementation of the subsequent motion-corrected iterative reconstruction. DiRespME-net is based on a U-Net architecture, and is trained in a self-supervised fashion, with a loss enforcing image similarity and spatial smoothness of the motion fields. Motion predicted by DiRespME-net was used for GPU-based motion-corrected CMRA in 12 test subjects and final images were compared to those produced by state-of-the-art reconstruction. Vessel sharpness and visible length of the right coronary artery (RCA) and the left anterior descending (LAD) coronary artery were used as metrics of image quality for comparison.
dc.description.abstractResults: No statistically significant difference in image quality was found between images reconstructed with the proposed approach (MC:DiRespME-net) and a motion-corrected reconstruction using cubic B-splines (MC:Niftyreg). Visible vessel length was not significantly different between methods (RCA: MC:Nifty-reg 5.7 +/- 1.7 cm vs MC:DiRespME-net 5.8 +/- 1.7 cm, P = 0.32; LAD: MC:Nifty-reg 7.0 +/- 2.6 cm vs MC:DiRespME-net 6.9 +/- 2.7 cm, P = 0.81). Similarly, no statistically significant difference between methods was observed in terms of vessel sharpness (RCA: MC:Nifty-reg 60.3 +/- 7.2% vs MC:DiRespME-net 61.0 +/- 6.8%, P = 0.19; LAD: MC:Nifty-reg 57.4 +/- 7.9% vs MC:DiRespME-net 58.1 +/- 7.5%, P = 0.27). The proposed approach achieved a 50-fold reduction in computation time, resulting in a total reconstruction time of approximately 20 s.
dc.description.abstractConclusions: The proposed self-supervised learning-based motion corrected reconstruction enables fast motion corrected CMRA image reconstruction, holding promise for integration in clinical routine.
dc.fechaingreso.objetodigital03-04-2024
dc.format.extent9 páginas
dc.fuente.origenWOS
dc.identifier.doi10.1016/j.mri.2021.10.004
dc.identifier.eissn1873-5894
dc.identifier.issn0730-725X
dc.identifier.pubmedidMEDLINE:34655727
dc.identifier.urihttps://doi.org/10.1016/j.mri.2021.10.004
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/78958
dc.identifier.wosidWOS:000712140600003
dc.information.autorucFacultad de Ingeniería; Prieto Vasquez, Claudia Del Carmen; S/I; 14195
dc.language.isoen
dc.nota.accesocontenido completo
dc.pagina.final18
dc.pagina.inicio10
dc.publisherELSEVIER SCIENCE INC
dc.revistaMAGNETIC RESONANCE IMAGING
dc.rightsacceso abierto
dc.subjectCoronary MR angiography
dc.subjectdeep learning
dc.subject3D whole-heart
dc.subjectmotion estimation
dc.subjectmotion correction
dc.subjectIMAGE REGISTRATION
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleSelf-supervised learning-based diffeomorphic non-rigid motion estimation for fast motion-compensated coronary MR angiography
dc.typeartículo
dc.volumen85
sipa.codpersvinculados14195
sipa.indexWOS
sipa.trazabilidadCarga SIPA;09-01-2024
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2024-04-03. Self-supervised learning-based diffeomorphic non-rigid motion estimation for fast motion-compensated coronary MR angiography.pdf
Size:
6.59 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas