{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:13:21Z","timestamp":1780989201379,"version":"3.54.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011055","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T00:00:00Z","timestamp":1683158400000}}],"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T00:00:00Z","timestamp":1682294400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"crossref","award":["MR\/S032290\/1"],"award-info":[{"award-number":["MR\/S032290\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100007759","name":"Dorothy M. Davis Heart and Lung Research Institute","doi-asserted-by":"publisher","award":["RG2661\/17\/20"],"award-info":[{"award-number":["RG2661\/17\/20"]}],"id":[{"id":"10.13039\/100007759","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000274","name":"British heart foundation","doi-asserted-by":"crossref","award":["NH\/18\/1\/33511"],"award-info":[{"award-number":["NH\/18\/1\/33511"]}],"id":[{"id":"10.13039\/501100000274","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N02124X\/1"],"award-info":[{"award-number":["EP\/N02124X\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000317","name":"Action medical research","doi-asserted-by":"crossref","award":["GN2572"],"award-info":[{"award-number":["GN2572"]}],"id":[{"id":"10.13039\/501100000317","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["ERC-2017-StG-757923"],"award-info":[{"award-number":["ERC-2017-StG-757923"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Computational fluid dynamics (CFD) can be used to simulate vascular haemodynamics and analyse potential treatment options. CFD has shown to be beneficial in improving patient outcomes. However, the implementation of CFD for routine clinical use is yet to be realised. Barriers for CFD include high computational resources, specialist experience needed for designing simulation set-ups, and long processing times. The aim of this study was to explore the use of machine learning (ML) to replicate conventional aortic CFD with automatic and fast regression models. Data used to train\/test the model consisted of 3,000 CFD simulations performed on synthetically generated 3D aortic shapes. These subjects were generated from a statistical shape model (SSM) built on real patient-specific aortas (N = 67). Inference performed on 200 test shapes resulted in average errors of 6.01% \u00b13.12 SD and 3.99% \u00b10.93 SD for pressure and velocity, respectively. Our ML-based models performed CFD in \u223c0.075 seconds (4,000x faster than the solver). This proof-of-concept study shows that results from conventional vascular CFD can be reproduced using ML at a much faster rate, in an automatic process, and with reasonable accuracy.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011055","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T17:39:21Z","timestamp":1682357961000},"page":"e1011055","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":28,"title":["Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1185-2973","authenticated-orcid":true,"given":"Endrit","family":"Pajaziti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Montalt-Tordera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Capelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rapha\u00ebl","family":"Sivera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emilie","family":"Sauvage","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Quail","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia","family":"Schievano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek","family":"Muthurangu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,4,24]]},"reference":[{"issue":"1","key":"pcbi.1011055.ref001","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1136\/heartjnl-2015-308044","article-title":"Computational fluid dynamics modelling in cardiovascular medicine","volume":"102","author":"PD Morris","year":"2016","journal-title":"Heart"},{"issue":"December","key":"pcbi.1011055.ref002","first-page":"1","article-title":"Using 4D Cardiovascular Magnetic Resonance Imaging to Validate Computational Fluid Dynamics: A Case Study","volume":"3","author":"G Biglino","year":"2015","journal-title":"Frontiers in Pediatrics"},{"issue":"1","key":"pcbi.1011055.ref003","first-page":"1","article-title":"Clinical validation and assessment of aortic hemodynamics using computational fluid dynamics simulations from computed tomography angiography","volume":"17","author":"Y Zhu","year":"2018","journal-title":"BioMedical Engineering Online"},{"key":"pcbi.1011055.ref004","article-title":"Computational simulations for aortic coarctation: representative results from a sampling of patients","author":"JF LaDisa","year":"2011","journal-title":"Journal of Biomedical Engineering"},{"issue":"4","key":"pcbi.1011055.ref005","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1007\/s10439-012-0715-0","article-title":"Non-invasive hemodynamic assessment of aortic coarctation: validation with in vivo measurements","volume":"41","author":"L Itu","year":"2013","journal-title":"Annals of biomedical engineering"},{"issue":"2\u20133","key":"pcbi.1011055.ref006","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.ejvs.2022.05.027","article-title":"Association between blood flow pattern and rupture risk of abdominal aortic aneurysm based on computational fluid dynamics","volume":"64","author":"Y Qiu","year":"2022","journal-title":"European Journal of Vascular and Endovascular Surgery"},{"key":"pcbi.1011055.ref007","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.jocs.2017.07.006","article-title":"What is needed to make cardiovascular models suitable for clinical decision support? A viewpoint paper","volume":"24","author":"W Huberts","year":"2018","journal-title":"Journal of Computational Science"},{"key":"pcbi.1011055.ref008","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.media.2016.01.005","article-title":"A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI","volume":"30","author":"MR Avendi","year":"2016","journal-title":"Medical image analysis"},{"key":"pcbi.1011055.ref009","article-title":"Deep Learning Based Centerline-Aggregated Aortic Hemodynamics: An Efficient Alternative to Numerical Modelling of Hemodynamics","author":"P Yevtushenko","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"1","key":"pcbi.1011055.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-66225-0","article-title":"Accelerating massively parallel hemodynamic models of coarctation of the aorta using neural networks","volume":"10","author":"B Feiger","year":"2020","journal-title":"Scientific Reports"},{"key":"pcbi.1011055.ref011","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbiomech.2019.109544","article-title":"A feasibility study of deep learning for predicting hemodynamics of human thoracic aorta","volume":"99","author":"L Liang","year":"2020","journal-title":"Journal of Biomechanics"},{"issue":"10","key":"pcbi.1011055.ref012","first-page":"1","article-title":"Combining statistical shape modeling, CFD, and meta-modeling to approximate the patient-specific pressure-drop across the aortic valve in real-time","volume":"36","author":"MJMM Hoeijmakers","year":"2020","journal-title":"International Journal for Numerical Methods in Biomedical Engineering"},{"issue":"8","key":"pcbi.1011055.ref013","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1161\/STROKEAHA.107.510644","article-title":"Geometry of the carotid bifurcation predicts its exposure to disturbed flow","volume":"39","author":"SW Lee","year":"2008","journal-title":"Stroke"},{"issue":"11","key":"pcbi.1011055.ref014","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1007\/s11517-008-0420-1","article-title":"An image-based modeling framework for patient-specific computational hemodynamics","volume":"46","author":"L Antiga","year":"2008","journal-title":"Medical & biological engineering & computing"},{"key":"pcbi.1011055.ref015","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1117\/12.57955","volume-title":"Sensor fusion IV: control paradigms and data structures","author":"PJ Besl","year":"1992"},{"issue":"1","key":"pcbi.1011055.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12880-016-0142-z","article-title":"A statistical shape modelling framework to extract 3D shape biomarkers from medical imaging data: assessing arch morphology of repaired coarctation of the aorta","volume":"16","author":"JL Bruse","year":"2016","journal-title":"BMC medical imaging"},{"key":"pcbi.1011055.ref017","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-04747-4_1","volume-title":"International Workshop on Shape in Medical Imaging","author":"A B\u00f4ne","year":"2018"},{"issue":"8","key":"pcbi.1011055.ref018","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1109\/TMI.2009.2021652","article-title":"A framework for geometric analysis of vascular structures: application to cerebral aneurysms","volume":"28","author":"M Piccinelli","year":"2009","journal-title":"IEEE transactions on medical imaging"},{"issue":"2","key":"pcbi.1011055.ref019","first-page":"11","article-title":"TetGen, a Delaunay-based quality tetrahedral mesh generator","volume":"41","author":"S Hang","year":"2015","journal-title":"ACM Trans Math Softw"},{"issue":"2","key":"pcbi.1011055.ref020","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1002\/jmri.25773","article-title":"Distribution of blood flow velocity in the normal aorta: effect of age and gender","volume":"47","author":"J Garcia","year":"2018","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"2","key":"pcbi.1011055.ref021","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s002469910014","article-title":"Phase-velocity cine magnetic resonance imaging measurement of pulsatile blood flow in children and young adults: in vitro and in vivo validation","volume":"21","author":"A Powell","year":"2000","journal-title":"Pediatric cardiology"},{"issue":"136","key":"pcbi.1011055.ref022","doi-asserted-by":"crossref","first-page":"20170632","DOI":"10.1098\/rsif.2017.0632","article-title":"Computational tools for clinical support: a multi-scale compliant model for haemodynamic simulations in an aortic dissection based on multi-modal imaging data","volume":"14","author":"M Bonfanti","year":"2017","journal-title":"Journal of The Royal Society Interface"},{"key":"pcbi.1011055.ref023","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014."},{"key":"pcbi.1011055.ref024","article-title":"Algorithms for hyper-parameter optimization","volume":"24","author":"J Bergstra","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"pcbi.1011055.ref025","article-title":"Computing discrete Fr\u00e9chet distance","author":"T Eiter","year":"1994","journal-title":"Technical Report CD-TR 94\/64"},{"issue":"1","key":"pcbi.1011055.ref026","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","article-title":"Generative adversarial networks: An overview","volume":"35","author":"A Creswell","year":"2018","journal-title":"IEEE signal processing magazine"},{"key":"pcbi.1011055.ref027","doi-asserted-by":"crossref","unstructured":"Ranjan A, Bolkart T, Sanyal S, Black MJ. Generating 3D faces using convolutional mesh autoencoders. In: Proceedings of the European Conference on Computer Vision (ECCV); 2018. p. 704\u201320.","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"pcbi.1011055.ref028","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.neucom.2015.08.104","article-title":"Auto-encoder based dimensionality reduction","volume":"184","author":"Y Wang","year":"2016","journal-title":"Neurocomputing"},{"issue":"1","key":"pcbi.1011055.ref029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12880-020-00511-1","article-title":"Utility of deep learning networks for the generation of artificial cardiac magnetic resonance images in congenital heart disease","volume":"20","author":"GP Diller","year":"2020","journal-title":"BMC Medical Imaging"},{"issue":"2","key":"pcbi.1011055.ref030","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1080\/00401706.1987.10488205","article-title":"Large sample properties of simulations using Latin hypercube sampling","volume":"29","author":"M Stein","year":"1987","journal-title":"Technometrics"},{"key":"pcbi.1011055.ref031","doi-asserted-by":"crossref","unstructured":"Abbas A, Rafiee A, Haase M, Malcolm A. Geometric Convolutional Neural Networks\u2013A Journey to Surrogate Modelling of Maritime CFD. In: The 9th Conference on Computational Methods in Marine Engineering (Marine 2021); 2022. p. 1\u20138.","DOI":"10.2218\/marine2021.6838"},{"key":"pcbi.1011055.ref032","article-title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","author":"CR Qi","year":"2016","journal-title":"CVPR 2017 Open Access"},{"issue":"4","key":"pcbi.1011055.ref033","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201325","article-title":"Learning Three-Dimensional Flow for Interactive Aerodynamic Design regression prediction for new shape","volume":"37","author":"N Umetani","year":"2018","journal-title":"ACM Trans Graph"},{"key":"pcbi.1011055.ref034","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D. Weight uncertainty in neural network. In: International conference on machine learning. PMLR; 2015. p. 1613\u201322."},{"issue":"1","key":"pcbi.1011055.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12968-022-00891-z","article-title":"Automatic segmentation of the great arteries for computational hemodynamic assessment","volume":"24","author":"J Montalt-Tordera","year":"2022","journal-title":"Journal of Cardiovascular Magnetic Resonance"},{"issue":"4","key":"pcbi.1011055.ref036","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1093\/ejcts\/ezs388","article-title":"A computational fluid dynamics study on geometrical influence of the aorta on haemodynamics","volume":"43","author":"KM Tse","year":"2013","journal-title":"European Journal of Cardio-Thoracic Surgery"},{"key":"pcbi.1011055.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10255842.2022.2128672","article-title":"Statistical shape representation of the thoracic aorta: accounting for major branches of the aortic arch","author":"H Wiputra","year":"2022","journal-title":"Computer methods in biomechanics and biomedical engineering"},{"issue":"2","key":"pcbi.1011055.ref038","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s13239-013-0146-6","article-title":"A review on computational fluid dynamics modelling in human thoracic aorta","volume":"4","author":"AD Caballero","year":"2013","journal-title":"Cardiovascular Engineering and Technology"},{"issue":"11","key":"pcbi.1011055.ref039","doi-asserted-by":"crossref","first-page":"1851","DOI":"10.1016\/j.jbiomech.2013.04.028","article-title":"Numerical and experimental assessment of turbulent kinetic energy in an aortic coarctation","volume":"46","author":"J Lantz","year":"2013","journal-title":"Journal of biomechanics"},{"issue":"1","key":"pcbi.1011055.ref040","doi-asserted-by":"crossref","DOI":"10.1115\/1.4037857","article-title":"Impact of patient-specific inflow velocity profile on hemodynamics of the thoracic aorta","volume":"140","author":"P Youssefi","year":"2018","journal-title":"Journal of biomechanical engineering"},{"issue":"1","key":"pcbi.1011055.ref041","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.jbiomech.2012.10.012","article-title":"Inflow boundary conditions for image-based computational hemodynamics: impact of idealized versus measured velocity profiles in the human aorta","volume":"46","author":"U Morbiducci","year":"2013","journal-title":"Journal of biomechanics"},{"issue":"5","key":"pcbi.1011055.ref042","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1109\/TMI.2021.3057496","article-title":"Synthetic Database of Aortic Morphometry and Hemodynamics: Overcoming Medical Imaging Data Availability","volume":"40","author":"B Thamsen","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"2","key":"pcbi.1011055.ref043","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s11517-008-0359-2","article-title":"The arterial windkessel","volume":"47","author":"N Westerhof","year":"2009","journal-title":"Medical & biological engineering & computing"},{"issue":"11","key":"pcbi.1011055.ref044","doi-asserted-by":"crossref","first-page":"e3134","DOI":"10.1002\/cnm.3134","article-title":"Patient-specific CFD modelling in the thoracic aorta with PC-MRI\u2013based boundary conditions: A least-square three-element Windkessel approach","volume":"34","author":"RM Romarowski","year":"2018","journal-title":"International journal for numerical methods in biomedical engineering"},{"issue":"4","key":"pcbi.1011055.ref045","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.1007\/s10439-010-9949-x","article-title":"Quantification of hemodynamics in abdominal aortic aneurysms during rest and exercise using magnetic resonance imaging and computational fluid dynamics","volume":"38","author":"AS Les","year":"2010","journal-title":"Annals of biomedical engineering"},{"issue":"1","key":"pcbi.1011055.ref046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12938-018-0497-1","article-title":"The effect of inlet and outlet boundary conditions in image-based CFD modeling of aortic flow","volume":"17","author":"S Madhavan","year":"2018","journal-title":"Biomedical engineering online"},{"key":"pcbi.1011055.ref047","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.jbiomech.2017.06.005","article-title":"On the choice of outlet boundary conditions for patient-specific analysis of aortic flow using computational fluid dynamics","volume":"60","author":"S Pirola","year":"2017","journal-title":"Journal of biomechanics"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011055","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T00:00:00Z","timestamp":1683158400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T18:13:22Z","timestamp":1683224002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011055"}},"subtitle":[],"editor":[{"given":"Daniel A.","family":"Beard","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,4,24]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011055","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1011055","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,24]]}}}