Related Experiment Video
Updated: Nov 20, 2025
Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
Published on: December 6, 2024
Prediction of 3D Cardiovascular hemodynamics before and after coronary artery bypass surgery via deep learning
Gaoyang Li1, Haoran Wang1,2, Mingzi Zhang1
1Institute of Fluid Science, Tohoku University, 2-1-1, Katahira, Aoba-ku, Sendai, Miyagi, 980-8577, Japan.
Insights
This study introduces a deep learning network for fast and accurate cardiovascular hemodynamics prediction, significantly reducing computational time for coronary heart disease treatment planning.
Area of Science:
- Biomedical Engineering
- Computational Biology
- Medical Imaging
Background:
- Clinical treatment planning for coronary heart disease relies on hemodynamic parameters.
- Computational fluid dynamics (CFD) is used for cardiovascular hemodynamics simulation but is computationally expensive for patient-specific models.
- High computational cost and complexity of CFD limit its clinical application.
Purpose of the Study:
- To develop a computationally efficient deep learning method for predicting cardiovascular hemodynamics.
- To overcome the limitations of traditional CFD in patient-specific modeling.
- To provide accurate hemodynamic insights for clinical treatment planning.
Main Methods:
- Development of cardiovascular hemodynamic point datasets.
- Creation of a dual sampling channel deep learning network.
- Analysis of the relationship between cardiovascular geometry and internal hemodynamics.
Main Results:
- Deep learning predictions show agreement with conventional CFD methods.
- Calculation time reduced 600-fold compared to CFD.
- Achieved prediction accuracy of around 90% for over 2 million nodes.
- Enabled cardiovascular hemodynamics prediction within 1 second.
- Demonstrated universality for evaluating complex arterial systems.
Conclusions:
- The developed deep learning method offers a computationally efficient and accurate alternative to CFD for cardiovascular hemodynamics.
- This approach meets the needs for clinical treatment planning of coronary heart disease.
- The method's speed and accuracy facilitate broader clinical application.
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.
