Inverse domain uncertainty quantification in hemodynamics: sampling virtual patient cohorts under constraints
Abstract
We consider the following inverse domain uncertainty quantification problem: given a prescribed value or measurement of a hemodynamic biomarker, characterize the distribution of vascular geometries compatible with it. The problem is formulated as a Bayesian inverse problem in which a high-dimensional latent parameter encodes the cardiovascular shape and accounts for inter-patient variability. The parameter-to-observable map composes a conditional LDDMM stochastic interpolant generating the aortic surface with a high-performance numerical finite element solver for the unsteady incompressible Navier--Stokes equations, from which biomarkers of interest are evaluated. The map is nonlinear, high-dimensional and computationally expensive. To address the problem, we compare three ensemble strategies: ensemble adjusted Kalman inversion (EAKI), adaptive Bayesian updating with structural reliability (aBUS), and a Wasserstein--Fisher--Rao (WFR) sequential Monte Carlo scheme. The first two approaches are derivative-free. For the third method, we introduce a novel differentiable flow-matching surrogate that reduces the cost of a single forward map evaluation at the price of a distribution shift depending on the training distribution used for the surrogate. We apply the framework to the generation of virtual patient cohorts matching prescribed pressure drops along aortic geometries affected by coarctation, and we validate and compare the three methods on synthetic data.
Related
- Enhanced Uncertainty Quantification Variational Autoencoders for the Solution of Bayesian Inverse Problems
- Uncertainty Quantification of State Variables Trajectories in the Context of Inverse Problems: An Approach from Bayesian Inference and FDA
- Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks
- Subjective Risk Decomposition: A New View for Uncertainty Quantification
- Bagged Martingale Posteriors: Calibrated Uncertainty Quantification for Predictive Resampling
BibTeX
@misc{romor2026inverse,
title = {{Inverse domain uncertainty quantification in hemodynamics: sampling virtual patient cohorts under constraints}},
author = {Francesco Romor and Jose Rodrigo Rojo-Garcia and André-Alexander Zepernick and Ana Djurdjevac and Alfonso Caiazzo},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27869},
eprint = {2610.27869},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27869},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Inverse domain uncertainty quantification in hemodynamics: sampling virtual patient cohorts under constraints
AU - Francesco Romor
AU - Jose Rodrigo Rojo-Garcia
AU - André-Alexander Zepernick
AU - Ana Djurdjevac
AU - Alfonso Caiazzo
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.27869
UR - https://arxiv.org/abs/2610.27869
AB - We consider the following inverse domain uncertainty quantification problem: given a prescribed value or measurement of a hemodynamic biomarker, characterize the distribution of vascular geometries compatible with it. The problem is formulated as a Bayesian inverse problem in which a high-dimensional latent parameter encodes the cardiovascular shape and accounts for inter-patient variability. The parameter-to-observable map composes a conditional LDDMM stochastic interpolant generating the aortic surface with a high-performance numerical finite element solver for the unsteady incompressible Navier--Stokes equations, from which biomarkers of interest are evaluated. The map is nonlinear, high-dimensional and computationally expensive. To address the problem, we compare three ensemble strategies: ensemble adjusted Kalman inversion (EAKI), adaptive Bayesian updating with structural reliability (aBUS), and a Wasserstein--Fisher--Rao (WFR) sequential Monte Carlo scheme. The first two approaches are derivative-free. For the third method, we introduce a novel differentiable flow-matching surrogate that reduces the cost of a single forward map evaluation at the price of a distribution shift depending on the training distribution used for the surrogate. We apply the framework to the generation of virtual patient cohorts matching prescribed pressure drops along aortic geometries affected by coarctation, and we validate and compare the three methods on synthetic data.
ER -