Institute of Biomechanics, Graz University of Technology, Stremayrgasse 16/2, 8010 Graz, Austria.
Department of Structural Engineering, Norwegian University of Science and Technology (NTNU), Trondheim, Norway.
J R Soc Interface. 2021 Sep;18(182):20210411. doi: 10.1098/rsif.2021.0411. Epub 2021 Sep 8.
The constitutive modelling of soft biological tissues has rapidly gained attention over the last 20 years. Current constitutive models can describe the mechanical properties of arterial tissue. Predicting these properties from microstructural information, however, remains an elusive goal. To address this challenge, we are introducing a novel hybrid modelling framework that combines advanced theoretical concepts with deep learning. It uses data from mechanical tests, histological analysis and images from second-harmonic generation. In this first proof of concept study, our hybrid modelling framework is trained with data from 27 tissue samples only. Even such a small amount of data is sufficient to be able to predict the stress-stretch curves of tissue samples with a median coefficient of determination of = 0.97 from microstructural information, as long as one limits the scope to tissue samples whose mechanical properties remain in the range commonly encountered. This finding suggests that deep learning could have a transformative impact on the way we model the constitutive properties of soft biological tissues.
在过去的 20 年中，软生物组织的本构建模得到了迅速关注。目前的本构模型可以描述动脉组织的力学性能。然而，从微观结构信息预测这些性能仍然是一个难以实现的目标。为了解决这一挑战，我们引入了一种新颖的混合建模框架，将先进的理论概念与深度学习相结合。它使用来自机械测试、组织学分析和二次谐波产生图像的数据。在这项初步概念验证研究中，我们的混合建模框架仅使用 27 个组织样本的数据进行训练。即使只有这么少量的数据，也足以能够从微观结构信息预测组织样本的应力-应变曲线，只要将范围限制在机械性能仍在常见范围内的组织样本上。这一发现表明，深度学习可能会对我们建模软生物组织本构特性的方式产生变革性的影响。
