An Implementation of Patient-Specific Biventricular Mechanics Simulations With a Deep Learning and Computational Pipeline.
An Implementation of Patient-Specific Biventricular Mechanics Simulations With a Deep Learning and Computational Pipeline.
复制标题
DOI：
10.3389/fphys.2021.716597
复制
发表时间：
2021
影响因子：
4
通讯作者：
Nordsletten DA
中科院分区：
文献类型：
--
作者：
Miller R;Kerfoot E;Mauger C;Ismail TF;Young AA;Nordsletten DA
心脏的参数化患者特定模型能够定量分析心脏功能以及估计局部应力和固有组织刚度。然而，个性化模型的开发和后续模拟通常需要漫长的手动设置，从图像标记到生成有限元模型和分配边界条件。最近，通过使用机器学习技术，快速的患者特定有限元建模已经成为可能。在本文中，利用多个神经网络进行图像标记和瓣膜标志的检测，以及流线型数据集成，将用于生成患者特定双心室模型的管道应用于从不同人群（包括肥厚型和扩张型心肌病患者和健康志愿者）中获得的临床数据。来自跟踪标志的瓣膜运动以及从标记图像测量的腔体积用于驱动真实运动并估计被动组织刚度值。神经网络被证明可以准确地标记这些不同形态的心脏区域和特征。此外，各组之间的全局固有参数（例如组织各向异性和归一化主动张力）的差异说明了病理导致的组织组成和/或结构的相应潜在变化。这项研究表明，在一个多样化的队列中，成功应用了一个通用的管道进行双心室建模，并结合了人工智能解决方案。
Parameterised patient-specific models of the heart enable quantitative analysis of cardiac function as well as estimation of regional stress and intrinsic tissue stiffness. However, the development of personalised models and subsequent simulations have often required lengthy manual setup, from image labelling through to generating the finite element model and assigning boundary conditions. Recently, rapid patient-specific finite element modelling has been made possible through the use of machine learning techniques. In this paper, utilising multiple neural networks for image labelling and detection of valve landmarks, together with streamlined data integration, a pipeline for generating patient-specific biventricular models is applied to clinically-acquired data from a diverse cohort of individuals, including hypertrophic and dilated cardiomyopathy patients and healthy volunteers. Valve motion from tracked landmarks as well as cavity volumes measured from labelled images are used to drive realistic motion and estimate passive tissue stiffness values. The neural networks are shown to accurately label cardiac regions and features for these diverse morphologies. Furthermore, differences in global intrinsic parameters, such as tissue anisotropy and normalised active tension, between groups illustrate respective underlying changes in tissue composition and/or structure as a result of pathology. This study shows the successful application of a generic pipeline for biventricular modelling, incorporating artificial intelligence solutions, within a diverse cohort.
登录
查看更多内容
影响因子：
3.8
作者：
Bayer, J. D.;Blake, R. C.;Plank, G.;Trayanova, N. A.
通讯作者：
Trayanova, N. A.
影响因子：
3.5
作者：
Asner, Liya;Hadjicharalambous, Myrianthi;Chabiniok, Radomir;Peresutti, Devis;Sammut, Eva;Wong, James;Carr-White, Gerald;Chowienczyk, Philip;Lee, Jack;King, Andrew;Smith, Nicolas;Razavi, Reza;Nordsletten, David
通讯作者：
Nordsletten, David
影响因子：
17.6
作者：
Bizopoulos, Paschalis;Koutsouris, Dimitrios
通讯作者：
Koutsouris, Dimitrios
影响因子：
3.5
作者：
Chabiniok, R.;Moireau, P.;Chapelle, D.
通讯作者：
Chapelle, D.
DOI：
10.1016/j.jcmg.2011.08.017
发表时间：
2012-01
期刊：
JACC. Cardiovascular imaging
影响因子：
--
作者：
Dave JK;Halldorsdottir VG;Eisenbrey JR;Raichlen JS;Liu JB;McDonald ME;Dickie K;Wang S;Leung C;Forsberg F
通讯作者：
Forsberg F