VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dong, Xuanzhao, Zhu, Wenhui, Xiong, Yujian, Chen, Xiwen, Wang, Hao, Li, Xin, Cheng, Jiajun, Wang, Zhipeng, Tang, Shao, Dumitrascu, Oana, Wang, Yalin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914168632770560
author Dong, Xuanzhao
Zhu, Wenhui
Xiong, Yujian
Chen, Xiwen
Wang, Hao
Li, Xin
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
author_facet Dong, Xuanzhao
Zhu, Wenhui
Xiong, Yujian
Chen, Xiwen
Wang, Hao
Li, Xin
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2511_18763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
Dong, Xuanzhao
Zhu, Wenhui
Xiong, Yujian
Chen, Xiwen
Wang, Hao
Li, Xin
Cheng, Jiajun
Wang, Zhipeng
Tang, Shao
Dumitrascu, Oana
Wang, Yalin
Computer Vision and Pattern Recognition
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
title VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18763