🤖 AI Summary
High-quality coronary angiography data with annotated stenoses are scarce, hindering the clinical deployment of automated detection models. To address this limitation, this work proposes the OT-Bridge Editor framework, which formulates localized stenosis editing as an entropy-regularized optimal transport problem incorporating geometric priors. This approach enables the generation of high-fidelity synthetic data while preserving anatomical realism. The method substantially improves pixel-level editing accuracy and structural consistency, achieving relative performance gains of 27.8% on the ARCADE benchmark and 23.0% on a multi-center dataset. These enhancements effectively boost the performance of downstream stenosis detection tasks.
📝 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.