Identifying heterogeneous micromechanical properties of biological tissues via physics-informed neural networks

Wensi Wu, Mitchell Daneker, Kevin T. Turner, Matthew A. Jolley, Lu Lu
{"title":"Identifying heterogeneous micromechanical properties of biological tissues via physics-informed neural networks","authors":"Wensi Wu, Mitchell Daneker, Kevin T. Turner, Matthew A. Jolley, Lu Lu","doi":"arxiv-2402.10741","DOIUrl":null,"url":null,"abstract":"The heterogeneous micromechanical properties of biological tissues have\nprofound implications across diverse medical and engineering domains. However,\nidentifying the full-field heterogeneous elastic properties of soft materials\nusing traditional computational and engineering approaches is fundamentally\nchallenging due to difficulties in estimating local stress fields. Recently,\nthere has been a growing interest in using data-driven models to learn\nfull-field mechanical responses such as displacement and strain from\nexperimental or synthetic data. However, research studies on inferring the\nfull-field elastic properties of materials, a more challenging problem, are\nscarce, particularly for large deformation, hyperelastic materials. Here, we\npropose a novel approach to identify the elastic modulus distribution in\nnonlinear, large deformation hyperelastic materials utilizing physics-informed\nneural networks (PINNs). We evaluate the prediction accuracies and\ncomputational efficiency of PINNs, informed by mechanic features and\nprinciples, across three synthetic materials with structural complexity that\nclosely resemble real tissue patterns, such as brain tissue and tricuspid valve\ntissue. Our improved PINN architecture accurately estimates the full-field\nelastic properties, with relative errors of less than 5% across all examples.\nThis research has significant potential for advancing our understanding of\nmicromechanical behaviors in biological materials, impacting future innovations\nin engineering and medicine.","PeriodicalId":501061,"journal":{"name":"arXiv - CS - Numerical Analysis","volume":"220 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Numerical Analysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2402.10741","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The heterogeneous micromechanical properties of biological tissues have profound implications across diverse medical and engineering domains. However, identifying the full-field heterogeneous elastic properties of soft materials using traditional computational and engineering approaches is fundamentally challenging due to difficulties in estimating local stress fields. Recently, there has been a growing interest in using data-driven models to learn full-field mechanical responses such as displacement and strain from experimental or synthetic data. However, research studies on inferring the full-field elastic properties of materials, a more challenging problem, are scarce, particularly for large deformation, hyperelastic materials. Here, we propose a novel approach to identify the elastic modulus distribution in nonlinear, large deformation hyperelastic materials utilizing physics-informed neural networks (PINNs). We evaluate the prediction accuracies and computational efficiency of PINNs, informed by mechanic features and principles, across three synthetic materials with structural complexity that closely resemble real tissue patterns, such as brain tissue and tricuspid valve tissue. Our improved PINN architecture accurately estimates the full-field elastic properties, with relative errors of less than 5% across all examples. This research has significant potential for advancing our understanding of micromechanical behaviors in biological materials, impacting future innovations in engineering and medicine.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
通过物理信息神经网络识别生物组织的异质微机械特性
生物组织的异质微观力学特性对不同的医学和工程领域有着深远的影响。然而,由于难以估计局部应力场,使用传统计算和工程方法识别软材料的全场异质弹性特性具有根本性的挑战。最近,人们对使用数据驱动模型从实验或合成数据中学习位移和应变等全场机械响应越来越感兴趣。然而,推断材料的全场弹性特性是一个更具挑战性的问题,尤其是对于大变形、高弹性材料而言,这方面的研究还很少。在此,我们提出了一种利用物理信息神经网络(PINNs)识别非线性、大变形超弹性材料弹性模量分布的新方法。我们评估了 PINNs 在力学特征和原理的指导下,在三种结构复杂、与真实组织形态(如脑组织和三尖瓣组织)接近的合成材料中的预测精度和计算效率。我们改进的 PINN 架构能准确估计全场弹性特性,所有示例的相对误差均小于 5%。这项研究在促进我们对生物材料微机械行为的理解方面具有巨大潜力,将对未来的工程和医学创新产生影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Analysis of the SQP Method for Hyperbolic PDE-Constrained Optimization in Acoustic Full Waveform Inversion Detection of a piecewise linear crack with one incident wave Randomized quasi-Monte Carlo and Owen's boundary growth condition: A spectral analysis Energy stable gradient flow schemes for shape and topology optimization in Navier-Stokes flows Exponential time propagators for elastodynamics
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1