VAOT：面向视网膜视盘增强的血管感知最优传输
VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
AI总结：
VAOT通过结合最优传输目标和结构保持正则化器，提升视网膜图像增强效果，有效保持血管结构和端点完整性。
摘要：
彩色视网膜摄影（CFP）在诊断和监测视网膜疾病中至关重要，但其获取的变异性（例如光照变化）常会降低图像质量，这促使了鲁棒增强方法的出现。无配对增强流程通常基于GAN，但它们可能会扭曲临床关键的血管结构，改变血管拓扑和终点完整性。受这些结构变化的启发，我们提出了Vessel-Aware Optimal Transport（VAOT），一种结合最优传输目标和两个结构保持正则化器的框架：（i）基于骨架的损失以保持全球血管连通性，（ii）端点意识的损失以稳定局部终点。这些约束指导无配对设置下的学习，减少噪声同时保持血管结构。在合成退化基准和血管及病变分割的下游评估中，实验结果展示了所提方法在多个最先进的基线中的优越性。代码可在https://github.com/Retinal-Research/VAOT上获取。
英文摘要：
Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhancement pipelines are typically GAN-based, however, they can distort clinically critical vasculature, altering vessel topology and endpoint integrity. Motivated by these structural alterations, we propose Vessel-Aware Optimal Transport (\textbf{VAOT}), a framework that combines an optimal-transport objective with two structure-preserving regularizers: (i) a skeleton-based loss to maintain global vascular connectivity and (ii) an endpoint-aware loss to stabilize local termini. These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure. Experimental results on synthetic degradation benchmark and downstream evaluations in vessel and lesion segmentation demonstrate the superiority of the proposed methods against several state-of-the art baselines. The code is available at https://github.com/Retinal-Research/VAOT
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
