Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport

TL;DR

This paper introduces the OT-Bridge Editor, a novel method for generating synthetic coronary angiograms with geometric constraints to improve stenosis detection accuracy.

Contribution

It reformulates angiogram editing as a constrained entropic optimal transport problem, enabling precise geometric control during image synthesis.

Findings

Synthetic data improves stenosis detection by 27.8% on ARCADE benchmark.

Synthetic angiograms enhance detection by 23.0% on multi-center dataset.

The method achieves consistent qualitative improvements.

Abstract

The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Synthetic stenosis data provides a practical avenue to augment training sets, improving data quality, diversity, and distributional coverage, and enhancing detection precision and generalization. However, diffusion-based editing commonly relies on soft guidance in a noise-initialized reverse process, offering limited pixel-level precision and structure preservation. We propose the OT-Bridge Editor, which reframes localized editing as a constrained entropic optimal transport (OT) problem and leverages geometric information to steer the generation path, enabling stronger geometric control. Extensive experiments show that our synthesized angiograms consistently improve downstream stenosis detection, yielding substantial relative gains of 27.8% on the public ARCADE benchmark and 23.0% on our multi-center dataset, supported by consistent qualitative results.