Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning

Gaoyang Li,Youjun Liu,Makoto Ohta,Mingzi Zhang,Aike Qiao,Simon Tupin,Hitomi Anzai,Haoran Wang

doi:10.1038/s42003-020-01638-1

Abstract

The clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance. Computational fluid dynamics (CFD) is gradually used in the simulation of cardiovascular hemodynamics. However, for the patient-specific model, the complex operation and high computational cost of CFD hinder its clinical application. To deal with these problems, we develop cardiovascular hemodynamic point datasets and a dual sampling channel deep learning network, which can analyze and reproduce the relationship between the cardiovascular geometry and internal hemodynamics. The statistical analysis shows that the hemodynamic prediction results of deep learning are in agreement with the conventional CFD method, but the calculation time is reduced 600-fold. In terms of over 2 million nodes, prediction accuracy of around 90%, computational efficiency to predict cardiovascular hemodynamics within 1 second, and universality for evaluating complex arterial system, our deep learning method can meet the needs of most situations.

Highlights

The clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance
In this study, in order to accurately predict complex 3D cardiovascular hemodynamics with limited samples, new requirements to adapt to the flexibility and high resolution of the input geometry have been imposed on datasets and deep learning networks, which is the main technical problem and contribution of this study
Our results showed that calculation results of the deep learning and Computational fluid dynamics (CFD) methods were highly consistent, and the calculation efficiency was improved 600-fold

Summary

Introduction

The clinical treatment planning of coronary heart disease requires hemodynamic parameters to provide proper guidance. For the patient-specific model, the complex operation and high computational cost of CFD hinder its clinical application To deal with these problems, we develop cardiovascular hemodynamic point datasets and a dual sampling channel deep learning network, which can analyze and reproduce the relationship between the cardiovascular geometry and internal hemodynamics. In this study, in order to accurately predict complex 3D cardiovascular hemodynamics with limited samples, new requirements to adapt to the flexibility and high resolution of the input geometry have been imposed on datasets and deep learning networks, which is the main technical problem and contribution of this study. With the aim of predicting 3D hemodynamics in the real cardiovascular systems of patients with coronary stenosis (e.g., geometry containing aorta, coronary arteries, and bypass graft), we have proposed a new deep learning method that could predict the velocity field and pressure field based on the geometric features of the model. To the best of our knowledge, this study represents the first report describing deep learning techniques that can effectively and accurately predict 3D hemodynamics of complex cardiovascular system with small grafts and coronary branches with limited data

Objectives

Methods

Results

Conclusion