Geometric uncertainty in patient-specific cardiovascular modeling with convolutional dropout networks

Maher, Gabriel D.; Fleeter, Casey; Schiavazzi, Daniele E.; Marsden, Alison L.

doi:10.1016/j.cma.2021.114038

Cited by 13 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By ignoring inter-patient variability, this method is not personalized to each patient. As expected, these uncertainties in anatomy and boundary conditions significantly affect model predictions [78,2,62,60,34,67,32].…”

Section: Introductionsupporting

confidence: 55%

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Menon,

Khan,

Sexton

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Computational simulations of coronary artery blood flow are an emerging non-invasive tool for personalized clinical risk stratification and treatment planning. However, current simulations contend with two related challenges -- the lack of personalized flow distributions informed by patient-specific data, and incomplete anatomies in image-based models due to the exclusion of arteries smaller than the imaging resolution. We introduce a data-enabled, personalized and multi-scale flow simulation framework spanning large coronary arteries to myocardial microvasculature. It includes image-based coronary models combined with synthetic vasculature for arteries below the imaging resolution, myocardial blood flow simulated using Darcy models, and systemic circulation represented as lumped-parameter networks. Personalized flow distributions and model parameters are estimated using surrogate-based optimization informed by clinically measured CT myocardial perfusion imaging and cardiac function. We reveal substantial differences in flow distributions and clinical diagnosis metrics between the proposed personalized framework and empirical methods based on anatomy; these errors cannot be predicted a priori. This suggests virtual treatment planning tools would benefit from increased personalization informed by emerging imaging methods.

show abstract

Section: Introductionsupporting

confidence: 55%

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Menon,

Khan,

Sexton

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We added several seeds to this region and applied a region‐growing algorithm to get the full aortocoronary domain. We selected this hybrid method among others described in the literature 32,33 to avoid modern automatic approaches that require specific expert training 34 and can induce errors similar to manual segmentations 35 . The selected method is simpler and commonly employed among physicians.…”

Section: Methodsmentioning

confidence: 99%

“…training 34 and can induce errors similar to manual segmentations. 35 The selected method is simpler and commonly employed among physicians. An extensive range of voxel intensity values can be found in the coronary lumen due to factors like the presence of artifacts and tiny coronary arteries, whose diameters are comparable to the image resolution.…”

Section: Ccta Image Segmentationmentioning

confidence: 99%

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

Fernández‐Martínez,

González‐Fernández,

Nogales‐Asensio

et al. 2024

Numer Methods Biomed Eng

View full text Add to dashboard Cite

We examined the effect of minimal lumen segmentation uncertainty on Fractional Flow Reserve obtained from Coronary Computed Tomography Angiography . A total of 14 patient‐specific coronary models with different stenosis locations and degrees of severity were enrolled in this study. The optimal segmented coronary lumens were disturbed using intra and inter‐operator variations on the segmentation threshold. was evaluated in each case by 3D‐OD CFD simulations. The findings suggest that the sensitivity of to this type of uncertainty increases distally and with the stenosis severity. Cases with moderate or severe distal coronary lesions should undergo either exact and thorough segmentation operations or invasive FFR measurements, particularly if the is close to the cutoff (0.80). Therefore, we conclude that it is crucial to consider the lesion's location and degree of severity when evaluating results.

show abstract

“…The main sources of uncertainty may be ascribed to (1) boundary conditions, (2) geometry and (3) material parameters. Scarce literature is available on quantification and/or propagation of (1) boundary condition uncertainties 24,25 and (2) geometry uncertainties 26,27 . Regarding (3) material parameters, 28 compared the uncertainties of different non‐Newtonian viscosity models for small Reynolds numbers in an idealized bifurcation model of a vein, however surrogate uncertainties are neglected and ad‐hoc assumptions on the parameter statistics made.…”

Section: Introductionmentioning

confidence: 99%

“…Scarce literature is available on quantification and/or propagation of (1) boundary condition uncertainties 24,25 and (2) geometry uncertainties. 26,27 Regarding (3) material parameters, 28 compared the uncertainties of different non-Newtonian viscosity models for small Reynolds numbers in an idealized bifurcation model of a vein, however surrogate uncertainties are neglected and ad-hoc assumptions on the parameter statistics made. The authors are aware of only one study 29 that considered all sources (1-3), however for a Newtonian fluid only.…”

mentioning

confidence: 99%

A Bayesian approach to blood rheological uncertainties in aortic hemodynamics

Ranftl

Müller

Windberger

et al. 2022

Numer Methods Biomed Eng

View full text Add to dashboard Cite

Computational hemodynamics has received increasing attention recently.Patient-specific simulations require questionable model assumptions, for example, for geometry, boundary conditions, and material parameters. Consequently, the credibility of these simulations is much doubted, and rightly so. Yet, the matter may be addressed by a rigorous uncertainty quantification. In this contribution, we investigated the impact of blood rheological models on wall shear stress uncertainties in aortic hemodynamics obtained in numerical simulations. Based on shear-rheometric experiments, we compare the non-Newtonian Carreau model to a simple Newtonian model and a Reynolds number-equivalent Newtonian model. Bayesian Probability Theory treats uncertainties consistently and allows to include elusive assumptions such as the comparability of flow regimes. We overcome the prohibitively high computational cost for the simulation with a surrogate model, and account for the uncertainties of the surrogate model itself, too. We have two main findings: (1) The Newtonian models mostly underestimate the uncertainties as compared to the non-Newtonian model.(2) The wall shear stresses of specific persons cannot be distinguished due to largely overlapping uncertainty bands, implying that a more precise determination of person-specific blood rheological properties is necessary for personspecific simulations. While we refrain from a general recommendation for one rheological model, we have quantified the error of the uncertainty quantification associated with these modeling choices.

show abstract

Geometric uncertainty in patient-specific cardiovascular modeling with convolutional dropout networks

Cited by 13 publications

References 44 publications

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT

A Bayesian approach to blood rheological uncertainties in aortic hemodynamics

Contact Info

Product

Resources

About

Geometric uncertainty in patient-specific cardiovascular modeling with convolutional dropout networks

Cited by 13 publications

References 44 publications

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Personalized coronary and myocardial blood flow models incorporating CT perfusion imaging and synthetic vascular trees

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFRCT

A Bayesian approach to blood rheological uncertainties in aortic hemodynamics

Contact Info

Product

Resources

About

Impact of minimal lumen segmentation uncertainty on patient‐specific coronary simulations: A look at FFR_CT