Fast surrogate model predicts coronary blood flow from centerlines
CARS: a centerline-anchored attention surrogate for coronary blood flow on skeleton-generated lumen geometries
Computational Engineering, Finance, and Science
Summary
Computing blood flow in coronary arteries usually takes a long time using detailed computer simulations. The authors made a faster method called CARS that uses the artery's centerline and size to quickly estimate blood pressure and flow. This method produces results in seconds rather than minutes or hours and matches detailed simulations well for pressure-related measurements. However, the flow predictions are less accurate for some uses, requiring more work for certain applications.
What this means in practice
- •For medical device developers: Quickly estimate coronary blood pressure for device design and testing without slow full simulations.
- •For biomedical software engineers: Integrate fast surrogate blood flow predictions into clinical decision software to assist coronary assessment workflows.
Authors
Reza Akbarian Bafghi, Sukirt Thakur, Maziar Raissi
Abstract
When the parameter of a PDE surrogate is the flow domain itself, the key/value set of an attention model must encode that domain. We present CARS (Coronary Artery Rapid Surrogate), a learned surrogate for the finite-volume solution map of the steady incompressible Navier-Stokes equations on coronary lumens built from image-derived centerlines. CARS maps a centerline with per-point lumen radius and a scalar inlet flow rate to pressure and velocity at arbitrary query points. The attention focal set is the case's own centerline, so geometry fusion costs $O(N n_f)$ rather than $O(N^2)$ in the number of evaluation points. Trained per territory on $2{,}700$ OpenFOAM solutions with synthetic focal lesions, CARS reaches relative $\ell_2$ errors of $0.120/0.149$ (pressure/velocity) on left-coronary and $0.063/0.119$ on right-coronary test sets, in $87$~ms per case against a solver wall-clock of $572$-$1{,}063$~s. It outperforms four parameter-matched neural operators, and accuracy saturates eightfold below the operating focal count. Fractional flow reserve derived from the predicted pressure matches the CFD label at Pearson $r = 0.941/0.993$ and reproduces the $\mathrm{FFR}\le 0.8$ decision in $97.7\%/96.3\%$ of held-out cases. The predicted velocity does not satisfy continuity closely enough for derived quantities, and the weights are territory-specific.