Related Experiment Video
Updated: Jul 6, 2026
Monitoring the Wall Mechanics During Stent Deployment in a Vessel
Published on: May 8, 2012
Rapid prediction of wall shear stress in stenosed coronary arteries based on deep learning
Salwa Husam Alamir1, Vincenzo Tufaro2,3, Matilde Trilli1
1Department of Mechanical Engineering, University College London, London, United Kingdom.
Insights
This study introduces a fast deep learning model for predicting coronary artery wall shear stress (WSS), crucial for cardiovascular event prediction. The efficient method combines synthetic and real data, offering a clinically relevant solution.
Area of Science:
- Cardiovascular research
- Medical imaging analysis
- Computational fluid dynamics
Background:
- Coronary artery wall shear stress (WSS) measurement offers prognostic value for cardiovascular events.
- Computational Fluid Dynamics (CFD) is used for WSS assessment but is computationally intensive for clinical use.
- Deep learning (DL) shows promise for rapid WSS prediction, but often relies on limited or synthetic data.
Purpose of the Study:
- To develop and evaluate a time-efficient deep learning model for predicting coronary artery WSS.
- To investigate the efficacy of combining synthetic and real patient data for training WSS prediction models.
- To assess the clinical relevance and speed of the developed DL model for WSS analysis.
Main Methods:
- Implemented two synthetic data generation approaches.
- Combined synthetic data with real patient data for model training.
- Utilized a U-net architecture deep learning model for WSS prediction.
- Evaluated model performance using Normalised Mean Absolute Error (NMAE).
Main Results:
- The DL model achieved a Normalised Mean Absolute Error (NMAE) of 6.03%.
- Inference time for WSS prediction was significantly reduced to 0.35 seconds.
- The approach demonstrated improved data utilization by combining synthetic and real datasets.
Conclusions:
- The developed DL model provides a computationally efficient and accurate method for coronary artery WSS prediction.
- This approach enhances the clinical applicability of WSS measurement for predicting adverse cardiovascular events.
- Combining synthetic and real data effectively trains DL models for hemodynamics analysis.
Abstract:
There is increasing evidence that coronary artery wall shear stress (WSS) measurement provides useful prognostic information that allows prediction of adverse cardiovascular events. Computational Fluid Dynamics (CFD) has been extensively used in research to measure vessel physiology and examine the role of the local haemodynamic forces on the evolution of atherosclerosis. Nonetheless, CFD modelling remains computationally expensive and time-consuming, making its direct use in clinical practice inconvenient. A number of studies have investigated the use of deep learning (DL) approaches for fast WSS prediction. However, in these reports, patient data were limited and most of them used synthetic data generation methods for developing the training set. In this paper, we implement 2 approaches for synthetic data generation and combine their output with real patient data in order to train a DL model with a U-net architecture for prediction of WSS in the coronary arteries. The model achieved 6.03% Normalised Mean Absolute Error (NMAE) with inference taking only 0.35 s; making this solution time-efficient and clinically relevant.
More Related Videos
13:07Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
06:18Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
Published on: December 6, 2024
