PyTorch-FEA: Autograd-enabled Finite Element Analysis Methods with Applications for Biomechanical Analysis of Human Aorta

Liang, Liang; Liu, Minliang; Elefteriades, John A.; Sun, Wei

doi:10.1101/2023.03.27.533816

Cited by 1 publication

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To facilitate the integration of DNN and FEM, we implemented FEM using the basic functions in PyTorch, an open-source machine learning (ML) library. We refer the reader to our technical report about the implementation details and comparison with Abaqus [28], which shows that the discrepancy between our FEM implementation and Abaqus is negligible. Since both DNNs and FEM are implemented by using the same ML library, the integration can be made seamless.…”

Section: Circumferential Curve Decodingmentioning

confidence: 99%

Synergistic Integration of Deep Neural Networks and Finite Element Method with Applications for Biomechanical Analysis of Human Aorta

Liang

Liu

Elefteriades

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation: Patient-specific finite element analysis (FEA) has the potential to aid in the prognosis of cardiovascular diseases by providing accurate stress and deformation analysis in various scenarios. It is known that patient-specific FEA is time-consuming and unsuitable for time-sensitive clinical applications. To mitigate this challenge, machine learning (ML) techniques, including deep neural networks (DNNs), have been developed to construct fast FEA surrogates. However, due to the data-driven nature of these ML models, they may not generalize well on new data, leading to unacceptable errors. Methods: We propose a synergistic integration of DNNs and finite element method (FEM) to overcome each other's limitations. We demonstrated this novel integrative strategy in forward and inverse problems. For the forward problem, we developed DNNs using state-of-the-art architectures, and DNN outputs were then refined by FEM to ensure accuracy. For the inverse problem of heterogeneous material parameter identification, our method employs a DNN as regularization for the inverse analysis process to avoid erroneous material parameter distribution. Results: We tested our methods on biomechanical analysis of the human aorta. For the forward problem, the DNN-only models yielded acceptable stress errors in majority of test cases; yet, for some test cases that could be out of the training distribution (OOD), the peak stress errors were larger than 50%. The DNN-FEM integration eliminated the large errors for these OOD cases. Moreover, the DNN-FEM integration was magnitudes faster than the FEM-only approach. For the inverse problem, the FEM-only inverse method led to errors larger than 50%, and our DNN-FEM integration significantly improved performance on the inverse problem with errors less than 1%.

show abstract

Section: Circumferential Curve Decodingmentioning

confidence: 99%