PUNCH: Physics-informed Uncertainty-aware Network for Coronary Hemodynamics

TL;DR

PUNCH is a non-invasive, physics-informed neural network framework that accurately estimates coronary flow reserve from angiography, enabling better detection of microvascular dysfunction without invasive tools.

Contribution

It introduces a novel uncertainty-aware neural network approach that infers coronary blood flow from standard angiograms using physics-based models, without needing ground-truth flow data.

Findings

Validated on synthetic and clinical data with accurate CFR estimation.

Runs in approximately three minutes per patient on a single GPU.

Demonstrates potential to improve non-invasive diagnosis of coronary microvascular dysfunction.

Abstract

More than 10 million coronary angiograms are performed globally each year, providing a gold standard for detecting obstructive coronary artery disease. Yet, no obstructive lesions are identified in 70% of patients evaluated for ischemic heart disease. Up to half of these patients have undiagnosed, life-limiting coronary microvascular dysfunction (CMD), which remains under-detected due to the limited availability of invasive tools required to measure coronary flow reserve (CFR). Here, we introduce PUNCH, a non-invasive, uncertainty-aware framework for estimating CFR directly from standard coronary angiography. PUNCH integrates physics-informed neural networks with variational inference to infer coronary blood flow from first-principles models of contrast transport, without requiring ground-truth flow measurements or population-level training. The pipeline runs in approximately three minutes per patient on a single GPU. Validated on synthetic angiograms with controlled noise and imaging artifacts, as well as on clinical bolus thermodilution data from 20 patients, PUNCH demonstrates accurate and uncertainty-calibrated CFR estimation. This approach establishes a new paradigm for CMD diagnosis and illustrates how physics-informed inference can substantially expand the diagnostic utility of available clinical imaging.