Deep learning predicts 3D coronary blood flow from angiograms
Physics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation
Artificial Intelligence
Summary
Doctors often use pictures of blood vessels and simple pressure measurements to decide how to treat heart problems. But these methods miss 3D details and complex blood flow information. The authors developed a computer program that uses physics and deep learning to create detailed 3D blood flow maps from just two X-ray pictures. This helps predict how blood moves through narrowed vessels quickly and accurately, supporting better treatment decisions.
What this means in practice
- •For cardiologists: Assess patient coronary blood flow in 3D using only standard angiograms for diagnosis and intervention planning.
- •For medical imaging software developers: Integrate physics-informed deep learning to add rapid hemodynamic predictions into angiography analysis tools.$Commercial implications: Enables commercial software that enhances heart imaging platforms with predictive blood flow modeling for clinical use.
Authors
Xi Chen, Jianchuan Yang, Hongde Li, Guangxin He, Qiuyu Ye, Qiang Luo, Mao Chen, Wenqi Hu
Abstract
Clinical decision-making for coronary intervention relies mainly on angiography and fractional flow reserve (FFR). However, angiography is two-dimensional and lacks depth information for 3D lesion characterization, while FFR provides only a single functional index, offering limited hemodynamic insight. Among existing methods, numerical analysis is computationally expensive, whereas learning-based approaches require extensive supervision and often lack physical consistency. To address these limitations, we propose physics-informed hemodynamic modeling, an integrated deep learning framework for 3D coronary blood flow analysis from dual-view angiography. First, an attention-enhanced CNN reconstructs coronary geometry from angiography. The resulting point clouds are then mapped to a reference domain and Fourier-encoded for joint representation. A decoupled network separately predicts velocity and pressure fields, with embedded physical priors enabling efficient transfer across physiological conditions. Across 32 clinical patients evaluated under four flow conditions, the trans-stenotic pressure-drop mean absolute percentage error was 2.02%, while the velocity and pressure relative-L2 errors were 0.054 and 0.023, respectively. Validation against hospital-measured FFR further achieved 93.8% diagnostic accuracy (30/32; exact 95% CI, 79.2%-99.2%). The framework also supports illustrative revascularization comparisons and sparse-data assimilation, with the full angiography-to-hemodynamics pipeline completed within 20 minutes per patient.