Geometry‑Aware Hemodynamics via a Transformer Encoder and Anisotropic RBF Decoder

Accurate and rapid estimation of hemodynamic metrics, such as pressure and wall shear stress (WSS), is essential for diagnosing and managing 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 integrates 1D centerline and inlet flow rate into a transformer-based encoder, followed by an anisotropic Radial Basis Function (RBF) decoder that aligns with vessel morphology for continuous wall-based predictions. We also introduce a large synthetic dataset of 4,000 single-vessel coronary artery geometries with corresponding flow simulations, enabling robust training and evaluation. Evaluation on synthetic dataset demonstrates significant improvements in accuracy and computational efficiency, achieving orders-of-magnitude speedup over CFD. The method enables real-time, non-invasive FFR assessment and comprehensive hemodynamic analysis.