FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions
This work addresses a critical challenge in cardiovascular modeling for clinicians and researchers, offering a more efficient and integrated approach to boundary condition estimation, though it appears incremental by building on existing amortized inference methods.
The paper tackles the problem of boundary condition tuning in patient-specific cardiovascular modeling, particularly in open-loop models and anatomies with vascular lesions, by introducing a general amortized inference framework based on probabilistic flow that jointly estimates clinical targets, inflow features, and anatomical embeddings, demonstrating it on aorto-iliac bifurcation and coronary arterial tree models.
Boundary condition tuning is a fundamental step in patient-specific cardiovascular modeling. Despite an increase in offline training cost, recent methods in data-driven variational inference can efficiently estimate the joint posterior distribution of boundary conditions, with amortization of training efforts over clinical targets. However, even the most modern approaches fall short in two important scenarios: open-loop models with known mean flow and assumed waveform shapes, and anatomies affected by vascular lesions where segmentation influences the reachability of pressure or flow split targets. In both cases, boundary conditions cannot be tuned in isolation. We introduce a general amortized inference framework based on probabilistic flow that treats clinical targets, inflow features, and point cloud embeddings of patient-specific anatomies as either conditioning variables or quantities to be jointly estimated. We demonstrate the approach on two patient-specific models: an aorto-iliac bifurcation with varying stenosis locations and severity, and a coronary arterial tree.