Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields.

Autor: Pajaziti E; University College London, Institution of Cardiovascular Science, London, United Kingdom., Montalt-Tordera J; University College London, Institution of Cardiovascular Science, London, United Kingdom., Capelli C; University College London, Institution of Cardiovascular Science, London, United Kingdom., Sivera R; University College London, Institution of Cardiovascular Science, London, United Kingdom., Sauvage E; University College London, Institution of Cardiovascular Science, London, United Kingdom., Quail M; Great Ormond Street Hospital, Cardiac Unit, London, United Kingdom., Schievano S; University College London, Institution of Cardiovascular Science, London, United Kingdom., Muthurangu V; University College London, Institution of Cardiovascular Science, London, United Kingdom.
Jazyk: angličtina
Zdroj: PLoS computational biology [PLoS Comput Biol] 2023 Apr 24; Vol. 19 (4), pp. e1011055. Date of Electronic Publication: 2023 Apr 24 (Print Publication: 2023).
DOI: 10.1371/journal.pcbi.1011055
Abstrakt: 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% ±3.12 SD and 3.99% ±0.93 SD for pressure and velocity, respectively. Our ML-based models performed CFD in ∼0.075 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.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2023 Pajaziti et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje