Personalising left-ventricular biophysical models of the heart using parametric physics-informed neural networks
Personalising left-ventricular biophysical models of the heart using parametric physics-informed neural networks
复制标题
DOI：
10.1016/j.media.2021.102066
复制
发表时间：
2021-05-02
影响因子：
10.9
通讯作者：
Kozerke, Sebastian
中科院分区：
文献类型：
--
作者：
Buoso, Stefano;Joyce, Thomas;Kozerke, Sebastian
我们提出了一个参数化的物理信息神经网络，用于模拟个性化的左心室生物力学。神经网络以两种方式约束生物物理问题：(i)网络输出被限制在由捕获左心室特征变形的径向基函数构建的子空间中；（ii）用于训练的代价函数是专门为超弹性、各向异性、几乎不可压缩的活性材料量身定制的能量势函数。径向基是由非线性有限元模型和高分辨率心脏图像的解剖形状模型相结合的结果产生的。我们表明，通过将神经网络与简化的循环模型耦合，我们可以有效地生成计算成本低廉的心脏力学估计。我们的模型比使用的参考有限元模型快30倍，包括训练时间，同时在射血分数（-3%）、峰值收缩压（7%）、中风功（4%）和心肌应变（14%）的预测中产生令人满意的平均误差。这种基于物理的神经网络非常适合于用功能数据有效地增强心脏图像，并为训练深度网络分类器生成大量合成病例，同时它为感兴趣的特定患者提供高效的个性化和高水平的细节。(c) 2021提交人。这是一篇基于CC by-nc-nd许可的开放获取文章（http://creativecommons.org/licenses/by-nc-nd/4.0/）
We present a parametric physics-informed neural network for the simulation of personalised left ventricular biomechanics. The neural network is constrained to the biophysical problem in two ways: (i) the network output is restricted to a subspace built from radial basis functions capturing characteristic deformations of left ventricles and (ii) the cost function used for training is the energy potential functional specifically tailored for hyperelastic, anisotropic, nearly-incompressible active materials. The radial bases are generated from the results of a nonlinear Finite Element model coupled with an anatomical shape model derived from high-resolution cardiac images. We show that, by coupling the neural network with a simplified circulation model, we can efficiently generate computationally inexpensive estimations of cardiac mechanics. Our model is 30 times faster than the reference Finite Element model used, including training time, while yielding satisfactory average errors in the predictions of ejection fraction (-3%), peak systolic pressure (7%), stroke work (4%) and myocardial strains (14%). This physics-informed neural network is well suited to efficiently augment cardiac images with functional data and to generate large sets of synthetic cases for training deep network classifiers while it provides efficient personalization to the specific patient of interest with a high level of detail. (c) 2021 The Author(s). Published by Elsevier B.V.This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )