doi_dedup___::e225555a08a082ad8f53f179bc59c5d0 2023-01-27T05:32:10Z

10.1098/rsta.2020.0257 50|doiboost____::e225555a08a082ad8f53f179bc59c5d0 3211056089 50|od______1064::83eb0f76b60445d72bb7428a1b68ef1a oai:ora.ox.ac.uk:uuid:9fc4563a-07e1-41d1-8b99-31ce2f8ac027 50|od_______267::6d978e42c57dfc79d61a84ab5be28cb8 oai:pubmedcentral.nih.gov:8543046 od_______267::6d978e42c57dfc79d61a84ab5be28cb8 34689630 PMC8543046 10.1098/rsta.2020.0257 PMC8543046 34689630 Vicente Grau Abhirup Banerjee Ernesto Zacur Robin P. Choudhury Blanca Rodriguez Julia Camps Yoram Rudy Christopher M. Andrews 2021-10-01 Cardiac magnetic resonance (CMR) imaging is a valuable modality in the diagnosis and characterization of cardiovascular diseases, since it can identify abnormalities in structure and function of the myocardium non-invasively and without the need for ionizing radiation. However, in clinical practice, it is commonly acquired as a collection of separated and independent 2D image planes, which limits its accuracy in 3D analysis. This paper presents a completely automated pipeline for generating patient-specific 3D biventricular heart models from cine magnetic resonance (MR) slices. Our pipeline automatically selects the relevant cine MR images, segments them using a deep learning-based method to extract the heart contours, and aligns the contours in 3D space correcting possible misalignments due to breathing or subject motion first using the intensity and contours information from the cine data and next with the help of a statistical shape model. Finally, the sparse 3D representation of the contours is used to generate a smooth 3D biventricular mesh. The computational pipeline is applied and evaluated in a CMR dataset of 20 healthy subjects. Our results show an average reduction of misalignment artefacts from 1.82 ± 1.60 mm to 0.72 ± 0.73 mm over 20 subjects, in terms of distance from the final reconstructed mesh. The high-resolution 3D biventricular meshes obtained with our computational pipeline are used for simulations of electrical activation patterns, showing agreement with non-invasive electrocardiographic imaging. The automatic methodologies presented here for patient-specific MR imaging-based 3D biventricular representations contribute to the efficient realization of precision medicine, enabling the enhanced interpretability of clinical data, the digital twin vision through patient-specific image-based modelling and simulation, and augmented reality applications. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’. General Physics and Astronomy General Engineering General Mathematics Pipeline (computing) Cine mri Structure and function Cardiac magnetic resonance Magnetic resonance imaging medicine.diagnostic_test medicine Human heart Modality (human–computer interaction) 3D reconstruction Computer science Nuclear magnetic resonance 3. Good health 03 medical and health sciences 0302 clinical medicine 030218 Nuclear Medicine & Medical Imaging 03021801 Radiology/Image segmentation 03021801 Radiology/Image segmentation - deep learning/datum 030204 Cardiovascular System & Hematology 03020401 Aging-associated diseases/Heart diseases 030217 Neurology & Neurosurgery 03021701 Brain/Neural circuits Articles Research Articles cardiac mesh reconstruction cine MRI misalignment correction electrophysiological simulation ECGI Heart Humans Imaging, Three-Dimensional Magnetic Resonance Imaging Magnetic Resonance Imaging, Cine Magnetic Resonance Spectroscopy 2021-10-25 2021-10-25 2021-12-13 2021-01-01 2023-01-05 2021-05-28 2023-01-05 The Royal Society Crossref Philosophical transactions. Series A, Mathematical, physical, and engineering sciences Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences true false 0.8 dedup-result-decisiontree-v3 openorgs____::6a7b1b4c40a067a1f209de6867fe094d University of Oxford University of Oxford doi_dedup___::015b27b0b7c55649236bf23a5c75f817 10.6084/m9.figshare.15656924.v2 2021-01-01 The Royal Society 10.6084/m9.figshare.15656924 corda__h2020::27f89b49dee12d828cc0f90f51727204 823712 ec__________::EC::H2020 ec__________::EC::H2020::RIA CompBioMed2 doi_dedup___::be1ef3b30a8d7aa7e4dfe1570d5febf7 2021-01-01 10.6084/m9.figshare.15656927 The Royal Society 10.6084/m9.figshare.15656927.v1 doi_________::9f9f2328e11d379b14cb888209e33088 2021-01-01 10.6084/m9.figshare.15656924.v1 The Royal Society 2021-10-01 34689630 34689630 The Royal Society PMC8543046 PMC8543046 2023-01-05 Royal Society 2021-10-25 The Royal Society 10.1098/rsta.2020.0257 2023-01-05 34689630 10.1098/rsta.2020.0257 http://creativecommons.org/licenses/by/4.0/ https://ora.ox.ac.uk/objects/uuid:9fc4563a-07e1-41d1-8b99-31ce2f8ac027 10.1098/rsta.2020.0257 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8543046 2021-10-25 10.1098/rsta.2020.0257 https://royalsociety.org/journals/ethics-policies/data-sharing-mining/ https://doi.org/10.1098/rsta.2020.0257 2021-10-25 34689630 PMC8543046 10.1098/rsta.2020.0257 https://pubmed.ncbi.nlm.nih.gov/34689630 2021-10-01 34689630 PMC8543046 10.1098/rsta.2020.0257 http://europepmc.org/articles/PMC8543046