Blood Pressure Prediction for Coronary Artery Disease Diagnosis using Coronary Computed Tomography Angiography

TL;DR

This paper introduces an automated pipeline for extracting coronary geometry from CCTA scans and a diffusion-based model to predict blood pressure, enabling fast, non-invasive CAD diagnosis without extensive CFD simulations.

Contribution

The authors develop an end-to-end pipeline for coronary geometry extraction and a diffusion-based regression model for blood pressure prediction from CCTA data, reducing computational costs.

Findings

Achieved an R2 of 64.42% in blood pressure prediction.

Outperformed baseline models in accuracy.

Provided a scalable framework for non-invasive CAD assessment.

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 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.