Key result
Novel LDDMM framework generates 3D aortic shapes and random perturbations for hemodynamic uncertainty quantification.
Its licence doesn't allow us to show a copy here.
Answers are grounded in this paper and cite their sources.
The proposed LDDMM stochastic interpolant framework enables generative modeling and uncertainty quantification for 3D cardiovascular shapes, such as aortas.
We introduce a novel conditional stochastic interpolant framework for generative modeling of three-dimensional shapes. The method builds on a recent LDDMM-based registration approach to learn the conditional drift between geometries. By leveraging the resulting pull-back and push-forward operators, we extend this formulation beyond standard Cartesian grids to complex shapes and random variables defined on distinct domains. We present an application in the context of cardiovascular simulations, where aortic shapes are generated from an initial cohort of patients. The conditioning variable is a latent geometric representation defined by a set of centerline points and the radii of the corresponding inscribed spheres. This methodology facilitates both data augmentation for three-dimensional biomedical shapes, and the generation of random perturbations of controlled magnitude for a given shape. These capabilities are essential for quantifying the impact of domain uncertainties arising from medical image segmentation on the estimation of relevant biomarkers.
No takes yet. Share an insight, caveat, or question.
Katz et al. (2026) studied Cardiovascular simulations (aortic shapes). Conditional stochastic interpolant framework was evaluated on Domain uncertainty quantification in hemodynamics. A novel conditional stochastic interpolant framework using LDDMM-based registration generates three-dimensional aortic shapes and controlled random perturbations for domain uncertainty quantification.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: