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

2026-01-23

AI Summary

Coronary microvascular dysfunction (CMD) is frequently underdiagnosed due to the lack of safe, reproducible, non-invasive diagnostic tools. This work proposes PUNCH, a novel method that, for the first time, integrates physics-informed neural networks with variational inference to enable end-to-end, patient-specific estimation of coronary flow reserve (CFR) without requiring ground-truth flow labels or population-level training. Leveraging routine coronary angiography and a first-principles model of contrast transport, PUNCH also provides high-fidelity uncertainty quantification. In a cohort of 12 clinical patients, PUNCH-estimated CFR demonstrated excellent agreement with invasive thermodilution measurements (Pearson r = 0.90), with prediction intervals narrower than the variability observed in repeated invasive assessments. Furthermore, on synthetic data, the method’s uncertainty estimates exhibited a near-perfect correlation with actual errors (r = 0.997).

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• coronary microvascular dysfunction
• coronary flow reserve
• non-invasive diagnosis
• angiography
• uncertainty quantification

Innovation

• physics-informed neural networks
• uncertainty quantification
• coronary flow reserve
• variational inference
• non-invasive hemodynamics