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

Endrit Pajaziti, Javier Montalt-Tordera, Claudio Capelli, Raphaël Sivera, Emilie Sauvage, Michael Quail, Silvia Schievano and Vivek Muthurangu

PLOS Computational Biology, 2023, vol. 19, issue 4, 1-20

Abstract: 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.Author summary: In the clinical management of pediatric disease (namely congenital heart defects), the indications for ‘when’ and ‘how’ to intervene are often unclear. It has been found that haemodynamic modelling tools such as computational fluid dynamics (CFD) simulations are useful in assisting clinicians and surgeons to better understand patient conditions and establish any potential risk factors. While this tool remains useful in a research capacity, its separation from clinical settings is an ongoing hindrance which prevents the full adoption of CFD in healthcare. The translation of CFD towards clinics is a continuous challenge, due to large time, computational and human resource requirements for running simulations. The application of machine learning (ML) for exploring potential methods to transform conventional CFD into clinically-suitable models is a recent phenomenon which is gaining significant momentum.

Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011055 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 11055&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1011055

DOI: 10.1371/journal.pcbi.1011055

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().