Non-intrusive and semi-intrusive uncertainty quantification of a multiscale in-stent restenosis model

Ye, Dongwei; Nikishova, Anna; Veen, Lourens; Zun, Pavel; Hoekstra, Alfons G.

doi:10.1016/j.ress.2021.107734

Cited by 18 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These guidelines only refer to medical devices and pharmacokinetics, thus future efforts are needed to define suitable protocols and methods for wider biomedical applications. The criticality of computational model verification, uncertainty quantification, calibration and validation in the biomedical field is also demonstrated by recent publications (Marino et al, 2008;Luraghi et al, 2018;Nikishova et al, 2018Nikishova et al, , 2019Fleeter et al, 2020;Ye et al, 2021a;Curreli et al, 2021;Groen et al, 2021;Luraghi et al, 2021;Rapadamnaba et al, 2021).…”

Section: Challenges and Future Directions Verification Uncertainty Quantification Calibration And Validationmentioning

confidence: 96%

“…However, a robust uncertainty quantification or sensitivity analysis is generally lacking. Some contribution in this context derived from Hoekstra’s research group ( Nikishova et al, 2018 ; Nikishova et al, 2019 ; Ye et al, 2021a ), which proposed a workflow for the uncertainty quantification of a multiscale agent-based modeling framework of ISR. The authors stressed the high computational effort needed for these analyses if Monte Carlo methods are adopted and proposed developing surrogate models either for a sub-module ( Nikishova et al, 2019 ) or the entire framework ( Ye et al, 2021a ).…”

Section: Challenges and Future Directionsmentioning

confidence: 99%

“…Some contribution in this context derived from Hoekstra’s research group ( Nikishova et al, 2018 ; Nikishova et al, 2019 ; Ye et al, 2021a ), which proposed a workflow for the uncertainty quantification of a multiscale agent-based modeling framework of ISR. The authors stressed the high computational effort needed for these analyses if Monte Carlo methods are adopted and proposed developing surrogate models either for a sub-module ( Nikishova et al, 2019 ) or the entire framework ( Ye et al, 2021a ). Both approaches were up to 7-fold faster than the Monte Carlo method and provided acceptable estimates of the uncertainties, thus demonstrating their validity and potentiality in case of computationally intensive analyses.…”

Section: Challenges and Future Directionsmentioning

confidence: 99%

See 2 more Smart Citations

Multiscale Computational Modeling of Vascular Adaptation: A Systems Biology Approach Using Agent-Based Models

Corti

Colombo

Migliavacca

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

The widespread incidence of cardiovascular diseases and associated mortality and morbidity, along with the advent of powerful computational resources, have fostered an extensive research in computational modeling of vascular pathophysiology field and promoted in-silico models as a support for biomedical research. Given the multiscale nature of biological systems, the integration of phenomena at different spatial and temporal scales has emerged to be essential in capturing mechanobiological mechanisms underlying vascular adaptation processes. In this regard, agent-based models have demonstrated to successfully embed the systems biology principles and capture the emergent behavior of cellular systems under different pathophysiological conditions. Furthermore, through their modular structure, agent-based models are suitable to be integrated with continuum-based models within a multiscale framework that can link the molecular pathways to the cell and tissue levels. This can allow improving existing therapies and/or developing new therapeutic strategies. The present review examines the multiscale computational frameworks of vascular adaptation with an emphasis on the integration of agent-based approaches with continuum models to describe vascular pathophysiology in a systems biology perspective. The state-of-the-art highlights the current gaps and limitations in the field, thus shedding light on new areas to be explored that may become the future research focus. The inclusion of molecular intracellular pathways (e.g., genomics or proteomics) within the multiscale agent-based modeling frameworks will certainly provide a great contribution to the promising personalized medicine. Efforts will be also needed to address the challenges encountered for the verification, uncertainty quantification, calibration and validation of these multiscale frameworks.

show abstract

Section: Challenges and Future Directions Verification Uncertainty Quantification Calibration And Validationmentioning

confidence: 96%

Section: Challenges and Future Directionsmentioning

confidence: 99%

Section: Challenges and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale Computational Modeling of Vascular Adaptation: A Systems Biology Approach Using Agent-Based Models

Corti

Colombo

Migliavacca

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…The agent-based SMC model simulates the biological and mechanical states of each cell of the vessel, while the BF model provides the haemodynamics information as a function of the current vessel lumen shape. This multiscale model has been applied to investigate the effect of functional endothelium regeneration and the impact of stent deployment and design on restenosis [ 6 , 7 , 9 , 10 ]. Most recently, the effects of local blood flow dynamics with scenarios of adaptive and non-adaptive coronary vasculature on restenosis were studied based on the ISR2D model [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty quantification of a three-dimensional in-stent restenosis model with surrogate modelling

Zun

Krzhizhanovskaya

et al. 2022

J. R. Soc. Interface.

Self Cite

View full text Add to dashboard Cite

In-stent restenosis is a recurrence of coronary artery narrowing due to vascular injury caused by balloon dilation and stent placement. It may lead to the relapse of angina symptoms or to an acute coronary syndrome. An uncertainty quantification of a model for in-stent restenosis with four uncertain parameters (endothelium regeneration time, the threshold strain for smooth muscle cell bond breaking, blood flow velocity and the percentage of fenestration in the internal elastic lamina) is presented. Two quantities of interest were studied, namely the average cross-sectional area and the maximum relative area loss in a vessel. Owing to the high computational cost required for uncertainty quantification, a surrogate model, based on Gaussian process regression with proper orthogonal decomposition, was developed and subsequently used for model response evaluation in the uncertainty quantification. A detailed analysis of the uncertainty propagation is presented. Around 11% and 16% uncertainty is observed on the two quantities of interest, respectively, and the uncertainty estimates show that a higher fenestration mainly determines the uncertainty in the neointimal growth at the initial stage of the process. The uncertainties in blood flow velocity and endothelium regeneration time mainly determine the uncertainty in the quantities of interest at the later, clinically relevant stages of the restenosis process.

show abstract

“…In recent years, plenty of methods has been studied for constructing a surrogate model based on DCNN. The DCNN-based surrogate model construction methods mainly include the ship-ship collision risk classification method [18], the time-frequency information signal prediction method [11], the associated remaining useful life estimation method [21], the accident prediction method of highway-rail grade crossing [22], the sensor network modeling method [23], the uncertainty quantification method of blood flow [24], etc. For these methods, the common feature is that they all need a lot of labeled data to learn the parameters of DCNN models.…”

Section: Introductionmentioning

confidence: 99%

Physics-Informed Deep Monte Carlo Quantile Regression method for Interval Multilevel Bayesian Network-based Satellite Heat Reliability Analysis

Zheng¹,

Wen²,

Gong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Temperature field reconstruction is essential for analyzing satellite heat reliability. As a representative machine learning model, the deep convolutional neural network (DCNN) is a powerful tool for reconstructing the satellite temperature field. However, DCNN needs a lot of labeled data to learn its parameters, which is contrary to the fact that actual satellite engineering can only acquire noisy unlabeled data. To solve the above problem, this paper proposes an unsupervised method, i.e., the physics-informed deep Monte Carlo quantile regression method, for reconstructing temperature field and quantifying the aleatoric uncertainty caused by data noise.For one thing, the proposed method combines a deep convolutional neural network with the known physics knowledge to reconstruct an accurate temperature field using only monitoring point temperatures. For another thing, the proposed method can quantify the aleatoric uncertainty by the Monte Carlo quantile regression.Based on the reconstructed temperature field and the quantified aleatoric uncertainty, this paper models an interval multilevel Bayesian Network to analyze satellite heat reliability. Two case studies are used to validate the proposed method.

show abstract

Non-intrusive and semi-intrusive uncertainty quantification of a multiscale in-stent restenosis model

Cited by 18 publications

References 45 publications

Multiscale Computational Modeling of Vascular Adaptation: A Systems Biology Approach Using Agent-Based Models

Multiscale Computational Modeling of Vascular Adaptation: A Systems Biology Approach Using Agent-Based Models

Uncertainty quantification of a three-dimensional in-stent restenosis model with surrogate modelling

Physics-Informed Deep Monte Carlo Quantile Regression method for Interval Multilevel Bayesian Network-based Satellite Heat Reliability Analysis

Contact Info

Product

Resources

About