From Centerlines to Hemodynamics: Anisotropic RBF Decoders for Coronary Arteries

2026-05-26

AI Summary

Current methods for coronary hemodynamic assessment, such as fractional flow reserve (FFR) and computational fluid dynamics (CFD), are often limited by invasiveness, high computational cost, or slow inference speed. This work proposes the first neural operator framework that integrates a Transformer encoder with an anisotropic radial basis function (RBF) decoder aligned to vascular geometry, enabling efficient prediction of continuous pressure and wall shear stress fields from only a one-dimensional vessel centerline and inlet flow rate. Evaluated on two large-scale paired datasets—comprising both synthetic and real clinical data—the method significantly outperforms baseline approaches such as GNOT, reducing prediction error by 52% in multi-vessel scenarios while requiring only 1/13.8 of GNOT’s computational cost, thereby achieving fast, non-invasive, and highly accurate hemodynamic modeling.

Abstract

Accurate and rapid estimation of hemodynamic metrics, such as pressure and wall shear stress (WSS), is important for assessing the severity of Coronary Artery Disease (CAD). Existing approaches, including invasive Fractional Flow Reserve (FFR) measurements and computationally expensive Computational Fluid Dynamics (CFD) simulations, face challenges in invasiveness, cost, and speed. We present a framework for fast, non-invasive coronary hemodynamics prediction. The model encodes 1D vessel centerlines together with inlet flow rate using a transformer-based encoder, and predicts continuous wall-based fields via an anisotropic Radial Basis Function (RBF) decoder aligned with vessel morphology. To support training and evaluation, we introduce two datasets with paired steady-state OpenFOAM simulations: (i) a synthetic benchmark of 4,200 single-vessel geometries with controlled anatomical variations, and (ii) a multi-vessel dataset derived from ImageCAS including 4,800 cases spanning both right and left coronary arteries, generated by randomly introducing stenoses and varying physiologically plausible flow rates. Across both datasets, our method achieves lower pressure and WSS errors than strong neural-operator baselines (GNOT, Transolver, and ONO) at a fraction of the computational cost of CFD. On the multi-vessel dataset, using 1,024 anisotropic RBF centers our model reduces the mean relative L2 error by 52% compared to the best neural-operator baseline, while at 128 centers it requires 13.8x fewer FLOPs than GNOT and still outperforms all baselines. The single-vessel dataset is publicly available at https://huggingface.co/datasets/angioinsight/single-vessel-flow.

Problem

• coronary hemodynamics
• wall shear stress
• pressure estimation
• non-invasive assessment
• coronary artery disease

Innovation

• anisotropic RBF decoder
• coronary hemodynamics
• neural operator
• centerline-based modeling
• wall shear stress prediction