Blood Pressure Prediction for Coronary Artery Disease Diagnosis using Coronary Computed Tomography Angiography
This work addresses the need for scalable and accessible non-invasive CAD diagnosis tools by reducing manual burden and computational costs, though it is incremental as it builds on existing CFD and AI methods for a specific medical domain.
The paper tackled the problem of computationally expensive and time-consuming computational fluid dynamics (CFD) simulations for coronary blood flow analysis in coronary artery disease (CAD) diagnosis by developing an end-to-end pipeline and a diffusion-based regression model to predict coronary blood pressure directly from coronary computed tomography angiography (CCTA) features, achieving state-of-the-art performance with an R2 of 64.42%, RMSE of 0.0974, and normalized RMSE of 0.154.
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 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. We further introduce a diffusion-based regression model designed to predict coronary blood pressure directly from CCTA derived features, bypassing the need for slow CFD computation during inference. Evaluated on a dataset of simulated coronary hemodynamics, the proposed model achieves state of the art performance, with an R2 of 64.42%, a root mean squared error of 0.0974, and a normalized RMSE of 0.154, outperforming several baseline approaches. This work provides a scalable and accessible framework for rapid, non-invasive blood pressure prediction to support CAD diagnosis.