Related Experiment Video
Updated: May 28, 2026
Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
Computed Fluid Dynamics-Based Blood Pressure Prediction for Coronary Artery Disease Diagnosis Using Coronary Computed
Rene Lisasi1, Huan Huang1, William Pei1
1Department of Computer Science, Kennesaw State University, Marietta, GA 30060, USA.
Insights
This study introduces an automated pipeline and an Inverted Conditional Diffusion (ICD) model to predict coronary blood pressure from CCTA scans, overcoming computational costs of traditional CFD for CAD diagnosis.
Area of Science:
- Cardiovascular Imaging and Physiology
- Artificial Intelligence in Medicine
- Computational Fluid Dynamics
Background:
- Computational fluid dynamics (CFD) provides vital hemodynamic markers for coronary artery disease (CAD) diagnosis but is computationally intensive.
- Limitations in CFD hinder the creation of labeled hemodynamic data for AI model training and widespread clinical adoption of non-invasive CAD assessment.
- Current methods face challenges in integrating complex CFD simulations into large-scale clinical workflows.
Purpose of the Study:
- To develop an end-to-end pipeline for automated coronary geometry extraction from CCTA and streamline simulation data generation.
- To create an efficient method for learning coronary blood pressure distributions, reducing manual effort.
- To introduce a novel diffusion-based regression model (ICD) for direct coronary blood pressure prediction from CCTA, bypassing intensive CFD during inference.
Main Methods:
- An automated pipeline was developed for coronary geometry extraction from CCTA and simulation data generation.
- An Inverted Conditional Diffusion (ICD) model was introduced for direct coronary blood pressure prediction.
- The ICD model was trained and validated on CCTA datasets using Adam optimizer, Huber loss, and specific hyperparameters (weight decay 1×10-3, learning rate 1×10-5, batch size 100).
- Model performance was evaluated on simulated coronary hemodynamic cases.
Main Results:
- The ICD model demonstrated state-of-the-art performance in predicting coronary blood pressure.
- Compared to LSTM, the ICD model improved R2 score by 19.78%, reduced RMSE by 19.44%, and lowered NRMSE by 18%.
- Compared to MLP, the ICD model improved R2 score by 8.38%, reduced RMSE by 4.3%, and reduced NRMSE by 5.4%.
Conclusions:
- The developed pipeline and ICD model offer a scalable and accessible framework for rapid, non-invasive, CFD-based blood pressure prediction.
- This approach has the potential to significantly support the diagnosis of coronary artery disease.
- The findings pave the way for broader adoption of physiology-based CAD assessment in clinical practice.
Abstract:
Computational fluid dynamics (CFD)-based simulation of coronary blood flow provides valuable hemodynamic markers, such as pressure gradients, for diagnosing coronary artery disease (CAD). However, CFD is computationally expensive, time-consuming, and difficult to integrate into large-scale clinical workflows. These limitations restrict the availability of labeled hemodynamic data for training AI models and hinder the broad adoption of non-invasive, physiology-based CAD assessment. To address these challenges, we develop an end-to-end pipeline that automates coronary geometry extraction from coronary computed tomography angiography (CCTA), streamlines simulation data generation, and enables efficient learning of coronary blood pressure distributions. The pipeline reduces the manual burden associated with traditional CFD workflows while producing consistent training data. Furthermore, we introduce a diffusion-based regression model. Specifically, the inverted conditional diffusion (ICD) model is designed to predict coronary blood pressure directly from CCTA-derived features, thereby bypassing the need for computationally intensive CFD during inference. The proposed model is trained and validated on two CCTA datasets using the Adam optimizer with a weight decay of 1×10-3, a learning rate of 1×10-5, a batch size of 100, and Huber loss. It is then evaluated on a test set of ten simulated coronary hemodynamic cases. Experimental results demonstrate state-of-the-art performance. Compared with Long Short-Term Memory (LSTM), the proposed model improves the R2 score by 19.78%, reduces the root mean squared error (RMSE) by 19.44%, and lowers the normalized root mean squared error (NRMSE) by 18%. Compared with a multilayer perceptron (MLP), it improves the R2 score by 8.38%, reduces RMSE by 4.3%, and reduces NRMSE by 5.4%. This work represents a first step toward a scalable and accessible framework for rapid, non-invasive, CFD-based blood pressure prediction, with the potential to support CAD diagnosis.
More Related Videos
06:57Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images
Published on: September 22, 2023
06:18Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
Published on: December 6, 2024
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:28Imaging Studies for Cardiovascular System V: CT
01:10Pre-Procedural Guidelines for Assessing Blood Pressure
01:19Assessing Blood pressure using a doppler ultrasound
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:30Acute Coronary Syndrome III: Diagnostic Studies