Learning Reduced-Order Models for Cardiovascular Simulations with Graph Neural Networks
This work addresses accuracy limitations in cardiovascular modeling for medical applications, representing an incremental improvement over existing physics-based methods.
The paper tackles the problem of reduced accuracy in physics-based reduced-order models for cardiovascular simulations when dealing with complex anatomies or pathological conditions by developing a graph neural network approach that achieves errors below 2% for pressure and 3% for flow rate.
Reduced-order models based on physics are a popular choice in cardiovascular modeling due to their efficiency, but they may experience reduced accuracy when working with anatomies that contain numerous junctions or pathological conditions. We develop one-dimensional reduced-order models that simulate blood flow dynamics using a graph neural network trained on three-dimensional hemodynamic simulation data. Given the initial condition of the system, the network iteratively predicts the pressure and flow rate at the vessel centerline nodes. Our numerical results demonstrate the accuracy and generalizability of our method in physiological geometries comprising a variety of anatomies and boundary conditions. Our findings demonstrate that our approach can achieve errors below 2% and 3% for pressure and flow rate, respectively, provided there is adequate training data. As a result, our method exhibits superior performance compared to physics-based one-dimensional models, while maintaining high efficiency at inference time.