EndoBeams.jl: A Julia finite element package for beam-to-surface contact problems in cardiovascular mechanics

Bisighini, Beatrice; Aguirre, Miquel; Pierrat, Baptiste; Perrin, David; Avril, Stéphane

doi:10.1016/j.advengsoft.2022.103173

Cited by 5 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented model relies on previous work to develop an optimised framework for numerical simulations of frictional contact interactions between wire-like structures discretised using beam elements and rigid surfaces [Aguirre and Avril. (2020); Bisighini et al (2022)]. Based on this, here we proposed an efficient approach to simulate braided stent deployment, which allowed us to reduce the computational time required to collect the simulations needed for ML training.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…Since there is no clinical need to predict the stent configuration after an unsuccessful deployment, the virtual framework here proposed consists of two steps ( Figure 1 ): A first classification step that allows a priori determination of whether a simulation will be successful or not, followed by a regression step that provides an approximated solution of the deployed stent configuration. Moreover, in continuation with our previous work ( Bisighini et al., 2022 ), we propose a fast strategy to perform FE simulations of braided stent deployment to reduce the computational time required to build the HF dataset for training.…”

Section: Introductionmentioning

confidence: 86%

“…The simulations are performed using EndoBeams.jl, an in-house and open-source FE modelling framework for the numerical simulation of frictional contact interactions between beams and rigid surfaces ( Bisighini et al., 2022 ). This software has been validated against some public benchmark tests and the commercial software Abaqus (Simulia, Dassault Systems, Providence, RI, United States).…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Machine learning and reduced order modelling for the simulation of braided stent deployment

et al. 2023

Self Cite

View full text Add to dashboard Cite

Endoluminal reconstruction using flow diverters represents a novel paradigm for the minimally invasive treatment of intracranial aneurysms. The configuration assumed by these very dense braided stents once deployed within the parent vessel is not easily predictable and medical volumetric images alone may be insufficient to plan the treatment satisfactorily. Therefore, here we propose a fast and accurate machine learning and reduced order modelling framework, based on finite element simulations, to assist practitioners in the planning and interventional stages. It consists of a first classification step to determine a priori whether a simulation will be successful (good conformity between stent and vessel) or not from a clinical perspective, followed by a regression step that provides an approximated solution of the deployed stent configuration. The latter is achieved using a non-intrusive reduced order modelling scheme that combines the proper orthogonal decomposition algorithm and Gaussian process regression. The workflow was validated on an idealized intracranial artery with a saccular aneurysm and the effect of six geometrical and surgical parameters on the outcome of stent deployment was studied. We trained six machine learning models on a dataset of varying size and obtained classifiers with up to 95% accuracy in predicting the deployment outcome. The support vector machine model outperformed the others when considering a small dataset of 50 training cases, with an accuracy of 93% and a specificity of 97%. On the other hand, real-time predictions of the stent deployed configuration were achieved with an average validation error between predicted and high-fidelity results never greater than the spatial resolution of 3D rotational angiography, the imaging technique with the best spatial resolution (0.15 mm). Such accurate predictions can be reached even with a small database of 47 simulations: by increasing the training simulations to 147, the average prediction error is reduced to 0.07 mm. These results are promising as they demonstrate the ability of these techniques to achieve simulations within a few milliseconds while retaining the mechanical realism and predictability of the stent deployed configuration.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 86%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations