An Implementation of Patient-Specific Biventricular Mechanics Simulations With a Deep Learning and Computational Pipeline

Abstract

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.

Personalization of biomechanical simulations of the left ventricle by in-vivo cardiac DTI data: Impact of fiber interpolation methods

“…An alternative, would be a lumped-parameter model, however, resulting in an idealized pressure trace not directly representing the measured pressure. Another data-driven alternative would be to incorporate the active parameter as Lagrange multipliers in the model implementation, while including both, pressure and volume measurements as model inputs ( Asner et al, 2016 ; Miller et al, 2021 ). This option is, however, not part of the Living Heart Human model.…”

A Deep Learning Model for the Identification of Active Contraction Properties of the Myocardium Using Limited Clinical Metrics

“…The fast and accurate predictions made by the deep learning model have been used in diverse elds of studies of cardiovascular mechanics (Dabiri et al 2020;Galati et al 2022; Kadem et al 2022;Liang et al 2018;Madani et al 2019). Moreover, emerging advancements in medical imaging techniques and computational modeling methods enable the generation of patientspeci c computational ventricular models (Litjens et al 2019;Miller et al 2021;Romaszko et al 2021; Tang et al 2010). As a result, the development of deep learning models in conjunction with constitutive analysis represents a feasible opportunity for conducting further clinical studies using non-invasive procedures in realistic patient-speci c settings.…”

Introduction of a Novel Image-Based and Non-Invasive Method for the Estimation of Local Elastic Properties of Great Vessels

“…Over recent decades, the use of patient-specific numerical models has continued to grow for an increasing range of applications [1][2][3]. Recent technological advances in medical imaging and computational power have enabled the increased use of numerical patient-specific modeling, providing a reliable tool for the study of cardiovascular problems in a highly accurate way.…”