Abstract
Recently, the risk of thrombus formation in the left atrium (LA) has been assessed through patient-specific computational fluid dynamic (CFD) simulations, characterizing the complex 4D nature of blood flow in the left atrial appendage (LAA). Nevertheless, the vast computational resources and long computing times required by traditional CFD methods prevents its embedding in the clinical workflow of time-sensitive applications. In this study, two distinct deep learning (DL) architectures have been developed to receive the patient-specific LAA geometry as an input and predict the endothelial cell activation potential (ECAP), which is linked to the risk of thrombosis. The first network is based on a simple fully-connected network, while the latter also performs a dimensionality reduction of the variables. Both models have been trained with a synthetic dataset of 210 LAA geometries being able to accurately predict the ECAP distributions with an average error of 4.72% for the fully-connected approach and 5.75% for its counterpart. Most importantly, the obtention of the ECAP predictions was quasi-instantaneous, orders of magnitude faster than conventional CFD.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsData Availability
The files containing the code to reproduce this study can be downloaded from github.com/Xtaltec/DL-surrogate-CFD-LAA.
References
Di Achille, P., Tellides, G., Figueroa, C.A., Humphrey, J.D.: A haemodynamic predictor of intraluminal thrombus formation in abdominal aortic aneurysms. Proc. R. Soc. A: Math. Phys. Eng. Sci. 470(2172), 20140163–20140163 (2014)
Fernández-Pérez, G., Duarte, R., de la Calle, M.C., Calatayud, J., Sánchez González, J.: Analysis of left ventricular diastolic function using magnetic resonance imaging. Radiología (Engl. Ed.) 54(4), 295–305 (2012)
García-Isla, G., et al.: Sensitivity analysis of geometrical parameters to study haemodynamics and thrombus formation in the left atrial appendage. Int. J. Numer. Methods Biomed. Eng. 34(8), e3100 (2018)
Hirose, T., et al.: Left atrial function assessed by speckle tracking echocardiography as a predictor of new-onset non-valvular atrial fibrillation: results from a prospective study in 580 adults. Eur. Heart J. - Cardiovasc. Imaging 13(3), 243–250 (2011)
Liang, L., Liu, M., Martin, C., Sun, W.: A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis. J. R. Soc. Interface 15(138), 20170844 (2018)
Masci, A., et al.: The impact of left atrium appendage morphology on stroke risk assessment in atrial fibrillation: a computational fluid dynamics study. Front. Physiol. 9, 1938 (2019)
Mill, J., et al.: Optimal boundary conditions in fluid simulations for predicting occlude related thrombus formation in the left atria. In: Computational and Mathematical Biomedical Engineering, Sixth International Conference (2019)
Slipsager, J.M., et al.: Statistical shape clustering of left atrial appendages. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 32–39. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_4
Veronesi, F., et al.: Quantification of mitral apparatus dynamics in functional and ischemic mitral regurgitation using real-time 3-dimensional echocardiography. J. Am. Soc. Echocardiogr. 21(4), 347–354 (2008)
Wunderlich, N.C., Beigel, R., Swaans, M.J., Ho, S.Y., Siegel, R.J.: Percutaneous interventions for left atrial appendage exclusion: options, assessment, and imaging using 2D and 3D echocardiography. JACC: Cardiovasc. Imaging 8(4), 472–488 (2015)
Funding
This work was supported by the Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502), the Retos I+D project (DPI2015-71640-R) and the Retos investigación project (RTI2018-101193-B-I00).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Morales, X. et al. (2020). Deep Learning Surrogate of Computational Fluid Dynamics for Thrombus Formation Risk in the Left Atrial Appendage. In: Pop, M., et al. Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation, CRT-EPiggy and LV Full Quantification Challenges. STACOM 2019. Lecture Notes in Computer Science(), vol 12009. Springer, Cham. https://doi.org/10.1007/978-3-030-39074-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-39074-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-39073-0
Online ISBN: 978-3-030-39074-7
eBook Packages: Computer ScienceComputer Science (R0)