Personalising left-ventricular biophysical models of the heart using parametric physics-informed neural networks

Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X., 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org. https://www.tensorflow.org/. Abbasi-Sureshjani, S., Amirrajab, S., Lorenz, C., Weese, J., Pluim, J., Breeuwer, M., 2020. 4D semantic cardiac magnetic resonance image synthesis on xcat anatomical model. arXiv preprint arXiv:2002.07089 Alnæs, 2015, The FEniCS project version 1.5, Arch. Numer. Softw., 3 Balaban, 2017, High-resolution data assimilation of cardiac mechanics applied to a dyssynchronous ventricle, Int. J. Numer. Methods Biomed. Eng., 33, e2863, 10.1002/cnm.2863 Bernard, 2018, Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?, IEEE Trans. Med. Imaging, 37, 2514, 10.1109/TMI.2018.2837502 Bonet, 2001, Large strain viscoelastic constitutive models, Int. J. Solids Struct., 38, 10.1016/S0020-7683(00)00215-8 Bonet, 2008 Buoso, 2020, An MRI image-guided left-ventricular shape model embedding local physiological coordinates and directions, 2217 Buoso, 2019, Reduced-order modeling of blood flow for noninvasive functional evaluation of coronary artery disease, Biomech. Model. Mechanobiol., 18, 1867, 10.1007/s10237-019-01182-w Buoso, 2017, On-demand aerodynamics of integrally actuated membranes with feedback control, AIAA J., 55, 377, 10.2514/1.J054888 Carruth, 2016, Transmural gradients of myocardial structure and mechanics: implications for fiber stress and strain in pressure overload, Prog. Biophys. Mol. Biol., 122, 215, 10.1016/j.pbiomolbio.2016.11.004 Caruel, 2014, Dimensional reductions of a cardiac model for effective validation and calibration, Biomech. Model. Mechanobiol., 13, 897, 10.1007/s10237-013-0544-6 Chabiniok, 2016, Multiphysics and multiscale modelling, data-model fusion and integration of organ physiology in the clinic: ventricular cardiac mechanics, Interface Focus, 6, 20150083, 10.1098/rsfs.2015.0083 Charlton, 2019, Modeling arterial pulse waves in healthy aging: a database for in silico evaluation of hemodynamics and pulse wave indexes, Am. J. Physiology-Heart Circ. Physiol., 317, H1062, 10.1152/ajpheart.00218.2019 Chollet, F., et al., 2015. Keras. https://keras.io. Corral-Acero, 2020, The ‘digital twin to enable the vision of precision cardiology, Eur. Heart J., 10.1093/eurheartj/ehaa159 Del Santo, 2020, Data driven approximation of parametrized PDEs by reduced basis and neural networks, J. Comput. Phys., 10.1016/j.jcp.2020.109550 Fares, 2002, A differential equation for approximate wall distance, Int. J. Numer. Methods Fluids, 39, 743, 10.1002/fld.348 Farrar, 2016, Atlas-based ventricular shape analysis for understanding congenital heart disease, Prog. Pediatr. Cardiol., 43, 61, 10.1016/j.ppedcard.2016.07.010 Finsberg, 2017 Finsberg, 2018, Estimating cardiac contraction through high resolution data assimilation of a personalized mechanical model, J. Comput. Sci., 24, 85, 10.1016/j.jocs.2017.07.013 Fresca, S., Dede, L., Manzoni, A., 2020. A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized pdes. arXiv preprint arXiv:2001.04001 Hesthaven, 2018, Non-intrusive reduced order modeling of nonlinear problems using neural networks, J. Comput. Phys., 363, 55, 10.1016/j.jcp.2018.02.037 Holzapfel, 2009, Constitutive modelling of passive myocardium: a structurally based framework for material characterization, Philos. Trans. R. Soc. A, 367, 3445, 10.1098/rsta.2009.0091 Joyce, 2020, A machine learning approach to left ventricle mesh prediction from multi-slice MR images, 28, 2230 Joyce, 2019, 3D medical image synthesis by factorised representation and deformable model learning, 110 Kingma, D. P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 Lee, 2020, Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders, J. Comput. Phys., 404, 108973, 10.1016/j.jcp.2019.108973 Lewandowski, 2013, Preterm heart in adult life, Circulation, 127, 197, 10.1161/CIRCULATIONAHA.112.126920 Logg, 2012 Mancinella, 2019, A comparison of methods for gradient field estimation on simplicial meshes, Comput. Graph., 80, 37, 10.1016/j.cag.2019.03.005 Manzoni, 2012, Model reduction techniques for fast blood flow simulation in parametrized geometries, Int. J. Numer. Methods Biomed. Eng., 28, 604, 10.1002/cnm.1465 Maso Talou, 2020, Deep learning over reduced intrinsic domains for efficient mechanics of the left ventricle, Front. Phys., 8, 30, 10.3389/fphy.2020.00030 Mollro, 2019, Population-based priors in cardiac model personalisation for consistent parameter estimation in heterogeneous databases, Int. J. Numer. Methods Biomed. Eng., 35, e3158, 10.1002/cnm.3158 Neic, 2017, Efficient computation of electrograms and ECGs in human whole heart simulations using a reaction-eikonal model, J. Comput. Phys., 346, 191, 10.1016/j.jcp.2017.06.020 Nguyen-Thanh, 2020, A deep energy method for finite deformation hyperelasticity, Eur. J. Mech. A/Solids, 80, 103874, 10.1016/j.euromechsol.2019.103874 Pagani, S., Manzoni, A., Carlberg, K., 2019. Statistical closure modeling for reduced-order models of stationary systems by the romes method. arXiv:1901.02792 Paun, 2017, Patient independent representation of the detailed cardiac ventricular anatomy, Med. Image Anal., 35, 270, 10.1016/j.media.2016.07.006 Pfaller, 2020, Using parametric model order reduction for inverse analysis of large nonlinear cardiac simulations, Int. J. Numer. Methods Biomed. Eng., 36, e3320, 10.1002/cnm.3320 Pfaller, 2019, The importance of the pericardium for cardiac biomechanics: from physiology to computational modeling, Biomech. Model. Mechanobiol., 18, 503, 10.1007/s10237-018-1098-4 Potse, 2006, A comparison of monodomain and bidomain reaction-diffusion models for action potential propagation in the human heart, IEEE Trans. Biomed. Eng., 43, 242 Quarteroni, 2007, Numerical solution of parametrized Navier–Stokes equations by reduced basis methods, Numer. Methods Partial Differ. Equ., 23, 923, 10.1002/num.20249 Raissi, 2018, Deep hidden physics models: deep learning of nonlinear partial differential equations, J. Mach. Learn. Res., 19, 1 Ramachandran, P., Zoph, B., Le, Q. V., 2017. Searching for activation functions. arXiv preprint arXiv:1710.05941 Ronneberger, 2015, U-net: Convolutional networks for biomedical image segmentation, 234 Roth, 1986, A bidomain model for the extracellular potential and magnetic field of cardiac tissue, IEEE Trans. Biomed. Eng., 33, 467, 10.1109/TBME.1986.325804 Rowley, 2011, Model reduction for fluids, using balanced proper orthogonal decomposition, Int. J. Bifurc. Chaos, 15, 997, 10.1142/S0218127405012429 Sack, 2018, Construction and validation of subject-specific biventricular finite-element models of healthy and failing swine hearts from high-resolution DT-MRI, Front. Physiol., 9, 539, 10.3389/fphys.2018.00539 Simo, 1998 Suinesiaputra, 2018, Statistical shape modeling of the left ventricle: myocardial infarct classification challenge, IEEE J. Biomed. Health Inform., 22, 503, 10.1109/JBHI.2017.2652449 Toussaint, 2013, In vivo human cardiac fibre architecture estimation using shape-based diffusion tensor processing, Med. Image Anal., 17, 1243, 10.1016/j.media.2013.02.008 Westerhof, 2009, The arterial Windkessel, Med. Biol. Eng. Comput., 47, 131, 10.1007/s11517-008-0359-2 Young, 2009, Computational cardiac atlases: from patient to population and back, Exp. Physiol., 94, 578, 10.1113/expphysiol.2008.044081 Zhang, 2014, Atlas-based quantification of cardiac remodeling due to myocardial infarction, PLoS One, 9, 1, 10.1371/journal.pone.0110243 Zhuang, 2013, Challenges and methodologies of fully automatic whole heart segmentation: a review, J. Healthc. Eng., 4, 371, 10.1260/2040-2295.4.3.371 Zhuang, 2010, A registration-based propagation framework for automatic whole heart segmentation of cardiac MRI, IEEE Trans. Med. Imaging, 29, 1612, 10.1109/TMI.2010.2047112 Zhuang, 2016, Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI, Med. Image Anal., 31, 77, 10.1016/j.media.2016.02.006