Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The heterogeneous micromechanical properties of biological tissues have profound implications across diverse medical and engineering domains. However, identifying full‐field heterogeneous elastic properties of soft materials using traditional engineering approaches is fundamentally challenging due to difficulties in estimating local stress fields. Recently, there has been a growing interest in data‐driven models for learning full‐field mechanical responses, such as displacement and strain, from experimental or synthetic data. However, research studies on inferring full‐field elastic properties of materials, a more challenging problem, are scarce, particularly for large deformation, hyperelastic materials. Here, a physics‐informed machine learning approach is proposed to identify the elasticity map in nonlinear, large deformation hyperelastic materials. This study reports the prediction accuracies and computational efficiency of physics‐informed neural networks (PINNs) in inferring the heterogeneous elasticity maps across materials with structural complexity that closely resemble real tissue microstructure, such as brain, tricuspid valve, and breast cancer tissues. Further, the improved architecture is applied to three hyperelastic constitutive models: Neo‐Hookean, Mooney Rivlin, and Gent. The improved network architecture consistently produces accurate estimations of heterogeneous elasticity maps, even when there is up to 10% noise present in the training data.
The heterogeneous micromechanical properties of biological tissues have profound implications across diverse medical and engineering domains. However, identifying full‐field heterogeneous elastic properties of soft materials using traditional engineering approaches is fundamentally challenging due to difficulties in estimating local stress fields. Recently, there has been a growing interest in data‐driven models for learning full‐field mechanical responses, such as displacement and strain, from experimental or synthetic data. However, research studies on inferring full‐field elastic properties of materials, a more challenging problem, are scarce, particularly for large deformation, hyperelastic materials. Here, a physics‐informed machine learning approach is proposed to identify the elasticity map in nonlinear, large deformation hyperelastic materials. This study reports the prediction accuracies and computational efficiency of physics‐informed neural networks (PINNs) in inferring the heterogeneous elasticity maps across materials with structural complexity that closely resemble real tissue microstructure, such as brain, tricuspid valve, and breast cancer tissues. Further, the improved architecture is applied to three hyperelastic constitutive models: Neo‐Hookean, Mooney Rivlin, and Gent. The improved network architecture consistently produces accurate estimations of heterogeneous elasticity maps, even when there is up to 10% noise present in the training data.
No abstract
Background and Aims To explore male–female differences in aneurysm growth and clinical outcomes in a two-centre retrospective Dutch cohort study of adult patients with ascending aortic aneurysm (AscAA). Methods Adult patients in whom imaging of an AscAA (root and/or ascending: ≥40 mm) was performed between 2007 and 2022 were included. Aneurysm growth was analysed using repeated measurements at the sinuses of Valsalva (SoV) and tubular ascending aorta. Male–female differences were explored in presentation, aneurysm characteristics, treatment strategy, survival, and clinical outcomes. Results One thousand eight hundred and fifty-eight patients were included (31.6% female). Median age at diagnosis was 65.4 years (interquartile range: 53.4–71.7) for females and 59.0 years (interquartile range: 49.3–68.0) for males (P < .001). At diagnosis, females more often had tubular ascending aortic involvement (75.5% vs. 70.2%; P = .030) while males more often had SoV involvement (42.8% vs. 21.6%; P < .001). Maximum absolute aortic diameter, at any location, at diagnosis did not differ between females (45.0 mm) and males (46.5 mm; P = .388). In females, tubular ascending growth was faster (P < .001), whereas in males, SoV growth was faster (P = .005), corrected for covariates. Unadjusted 10-year survival was 72.5% [95% confidence interval (CI) 67.8%–77.6%] for females and 78.3% (95% CI 75.3%–81.3%) for males (P = .010). Twenty-three type A dissections occurred, with an incidence rate of 8.2/1000 patient-years (95% CI 4.4–14.1) in females and 2.4/1000 patient-years (95% CI 1.2–4.5) in males [incidence rate ratio females/males: 3.4 (95% CI 1.5–8.0; P = .004)]. Conclusions In patients having entered a diagnostic programme, involvement of aortic segments and age- and segment-related growth patterns differ between women and men with AscAA, particularly at an older age. Unravelling of these intertwined observations will provide a deeper understanding of AscAA progression and outcome in women and men and can be used as an evidence base for patient-tailored clinical guideline development.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.