Generating wall shear stress for coronary artery in real-time using neural networks: Feasibility and initial results based on idealized models.

Computational fluid dynamics (CFD) and medical imaging can be integrated to derive some important hemodynamic parameters such as wall shear stress (WSS). However, CFD suffers from a relatively long computational time that usually varies from dozens of minutes to hours. Machine learning is a popular tool that has been applied to many fields, and it can predict outcomes fast and even instantaneously in most applications. This study aims to use machine learning as an alternative to CFD for generating hemodynamic parameters in real-time diagnosis during medical examinations. To perform the feasibility study, we used CFD to model the blood flow in 2000 idealized coronary arteries, and the calculated WSS values in these models were used as the dataset for training and testing. The preparation of the dataset was automated by scripts programmed in Python, and OpenFOAM was used as the CFD solver. We have explored multivariate linear regression, multi-layer perceptron, and convolutional neural network architectures to generate WSS values from coronary artery geometry directly without CFD. These architectures were implemented in TensorFlow 2.0. Our results showed that these algorithms were able to generate results in less than 1 s, proving its capability in real-time applications, in terms of computational time. Based on the accuracy, convolutional neural network outperformed the other architectures with a normalized mean absolute error of 2.5%. Although this study is based on idealized models, to the best of our knowledge, it is the first attempt to predict WSS in a stenosed coronary artery using machine learning approaches.