A novel deep learning method predicted 3D cardiovascular hemodynamics with approximately 90% accuracy compared to conventional computational fluid dynamics, while reducing calculation time 600-fold.
Does a deep learning network accurately and efficiently predict 3D cardiovascular hemodynamics compared to conventional CFD in patients with coronary heart disease?
A novel deep learning method can predict 3D cardiovascular hemodynamics and FFR from CTA data with high accuracy in under 1 second, potentially enabling real-time clinical guidance for CABG surgery.
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.
Li et al. (Fri,) conducted a other in Coronary heart disease (n=110). Deep learning network vs. Computational fluid dynamics (CFD) was evaluated on Prediction accuracy and computational time. A novel deep learning method predicted 3D cardiovascular hemodynamics with approximately 90% accuracy compared to conventional computational fluid dynamics, while reducing calculation time 600-fold.