226 Advancing Neurovascular Diagnostics for Abnormal Hemodynamic Conditions Through AI-Driven Physics-informed Neural Networks

Abstract

INTRODUCTION: Many studies have explored the application of machine learning and neural networks in extracting critical diagnostic information from structural and functional medical imaging. While these methods show potential for improving efficiency, concerns arise when interpreting subtle imaging features, especially when training data is limited. Physics-informed neural networks (PINNs) address these issues by incorporating governing equations from physical and mechanical models into the analysis. METHODS: We examined the use of a PINN that enforces the convection equation, relating contrast media propagation to blood velocity, the Navier-Stokes equations for velocity and pressure distributions, and the conservation of mass requirement to calculate velocity and pressure distributions within patient-specific blood vessels. We also implemented a boundary condition that accounts for real contrast-media propagation from 1000 fps high-speed angiographic (HSA) image sequences, allowing for an assumption-free problem space within a medical imaging framework. Velocity fields and pressure gradients were calculated for flow in aneurysms and carotid bifurcations. RESULTS: Our method demonstrates comparable results to computational fluid dynamics (CFD) without requiring manual data processing, significantly improving the efficiency of calculating high-resolution velocity and pressure fields. By integrating AI with physics modeling, this novel approach holds the potential for advancing neurovascular diagnostics and providing more accurate, personalized treatment plans for patients with neurovascular pathologies. CONCLUSIONS: This innovative approach, integrating physics modeling and artificial intelligence, offers more accurate and personalized diagnostics for patients with neurovascular pathologies. The PINN method not only achieves results comparable to computational fluid dynamics without the need for manual data processing but also greatly enhances the efficiency of calculating high-resolution velocity and pressure fields.