Abstract
Patient-specific hemodynamics assessment could support diagnosis and treatment of neurovascular diseases. Currently, conventional medical imaging modalities are not able to accurately acquire high-resolution hemodynamic information that would be required to assess complex neurovascular pathologies. Instead, computational fluid dynamics (CFD) simulations can be applied to tomographic reconstructions to obtain clinically relevant information. However, three-dimensional (3D) CFD simulations require enormous computational resources and simulation-related expert knowledge that are usually not available in clinical environments. Recently, deep-learning-based methods have been proposed as CFD surrogates to improve computational efficiency. Nevertheless, the prediction of high-resolution transient CFD simulations for complex vascular geometries poses a challenge to conventional deep learning models. In this work, we present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries. For this, an octree-based spatial discretization is combined with an implicit neural function representation to efficiently handle the prediction of the 3D velocity field for each time step. The presented method is evaluated for the task of cerebral hemodynamics prediction before and during the injection of contrast agent in the internal carotid artery (ICA). Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m s\(^{-1}\), whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chnafa, C., et al.: Vessel calibre and flow splitting relationships at the internal carotid artery terminal bifurcation. Physiol. Meas. 38(11), 2044 (2017)
Chnafa, C., Brina, O., Pereira, V., Steinman, D.: Better than nothing: a rational approach for minimizing the impact of outflow strategy on cerebrovascular simulations. AJNR Am. J. Neuroradiol. 39(2), 337–343 (2018)
Du, P., Zhu, X., Wang, J.X.: Deep learning-based surrogate model for three-dimensional patient-specific computational fluid dynamics. Phys. Fluids 34(8), 081906 (2022)
Feiger, B., et al.: Accelerating massively parallel hemodynamic models of coarctation of the aorta using neural networks. Sci. Rep. 10(1), 9508 (2020)
Ferdian, E., et al.: 4DFlowNet: super-resolution 4D flow MRI using deep learning and computational fluid dynamics. Front. Phys. 8 (2020)
Ford, M.D., Alperin, N., Lee, S.H., Holdsworth, D.W., Steinman, D.A.: Characterization of volumetric flow rate waveforms in the normal internal carotid and vertebral arteries. Physiol. Meas. 26(4), 477–488 (2005)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770–778 (2016)
Hoi, Y., et al.: Characterization of volumetric flow rate waveforms at the carotid bifurcations of older adults. Physiol. Meas. 31(3), 291–302 (2010)
Izzo, R., Steinman, D., Manini, S., Antiga, L.: The vascular modeling toolkit: a python library for the analysis of tubular structures in medical images. J. Open Source Softw. 3(25), 745 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the ICLR (2015)
Li, G., et al.: Prediction of cerebral aneurysm hemodynamics with porous-medium models of flow-diverting stents via deep learning. Front. Physiol. 12, 733444 (2021)
Li, G., et al.: Prediction of 3D cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning. Commun. Biol. 4(1), 99 (2021)
Li, Z., et al.: Fourier neural operator for parametric partial differential equations. arXiv (2020)
Lu, L., Jin, P., Pang, G., Zhang, Z., Karniadakis, G.E.: Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators. Nat. Mach. Intell. 3(3), 218–229 (2021)
Meagher, D.: Geometric modeling using octree encoding. Comput. Graph. Image Process. 19(2), 129–147 (1982)
Meister, F., et al.: Fast automatic liver tumor radiofrequency ablation planning via learned physics model. In: Proceedings of the MICCAI, pp. 167–176 (2022)
Mendis, S., Puska, P., Norrving, B., Organization, W.H., Federation, W.H., Organization, W.S.: Global atlas on cardiovascular disease prevention and control (2011)
Mulder, G., Bogaerds, A., Rongen, P., van de Vosse, F.: The influence of contrast agent injection on physiological flow in the circle of Willis. Me. Eng. Phys. 33(2), 195–203 (2011)
Raissi, M., Yazdani, A., Karniadakis, G.E.: Hidden fluid mechanics: learning velocity and pressure fields from flow visualizations. Science 367(6481), 1026–1030 (2020)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of the MICCAI, pp. 234–241 (2015)
Rutkowski, D.R., Roldán-Alzate, A., Johnson, K.M.: Enhancement of cerebrovascular 4d flow MRI velocity fields using machine learning and computational fluid dynamics simulation data. Sci. Rep. 11(1), 10240 (2021)
Sun, Q., Groth, A., Aach, T.: Comprehensive validation of computational fluid dynamics simulations of in-vivo blood flow in patient-specific cerebral aneurysms. Med. Phys. 39(2), 742–754 (2012)
Taebi, A.: Deep learning for computational hemodynamics: a brief review of recent advances. Fluids 7(6), 197 (2022)
Waechter, I., Bredno, J., Hermans, R., Weese, J., Barratt, D.C., Hawkes, D.J.: Model-based blood flow quantification from rotational angiography. Med. Image Anal. 12(5), 586–602 (2008)
Wang, P.S., Liu, Y., Guo, Y.X., Sun, C.Y., Tong, X.: O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Trans. Graph. 36(4), 1–11 (2017)
Wang, P.S., Liu, Y., Tong, X.: Deep octree-based CNNs with output-guided skip connections for 3D shape and scene completion. In: Proceedings of the CVPRW, pp. 1074–1081 (2020)
Weber, J., Penn, J.: Creation and rendering of realistic trees. In: Proceedings of the SIGGRAPH, pp. 119–128. Association for Computing Machinery (1995)
Weller, H.G., Tabor, G., Jasak, H., Fureby, C.: A tensorial approach to computational continuum mechanics using object-oriented techniques. Comput. Phys. 12(6), 620–631 (1998)
Xie, Y., Franz, E., Chu, M., Thuerey, N.: tempoGAN: a temporally coherent, volumetric GAN for super-resolution fluid flow. ACM Trans. Graph. 37(4), 95 (2018)
Yuan, X.Y., et al.: Real-time prediction of transarterial drug delivery based on a deep convolutional neural network. Appl. Sci. 12(20), 10554 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Maul, N. et al. (2023). Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model. In: Frangi, A., de Bruijne, M., Wassermann, D., Navab, N. (eds) Information Processing in Medical Imaging. IPMI 2023. Lecture Notes in Computer Science, vol 13939. Springer, Cham. https://doi.org/10.1007/978-3-031-34048-2_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-34048-2_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34047-5
Online ISBN: 978-3-031-34048-2
eBook Packages: Computer ScienceComputer Science (R0)