BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Cheng, Xie, Weizheng, Gao, Fan, Liu, Yutong, Wu, Ruoling, Han, Zeyu, Qiu, Jingxi, Wang, Xiangxiang, Yang, Zhenglin, Wang, Hao, Yu, Yongbin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909812986478592
author Huang, Cheng
Xie, Weizheng
Gao, Fan
Liu, Yutong
Wu, Ruoling
Han, Zeyu
Qiu, Jingxi
Wang, Xiangxiang
Yang, Zhenglin
Wang, Hao
Yu, Yongbin
author_facet Huang, Cheng
Xie, Weizheng
Gao, Fan
Liu, Yutong
Wu, Ruoling
Han, Zeyu
Qiu, Jingxi
Wang, Xiangxiang
Yang, Zhenglin
Wang, Hao
Yu, Yongbin
contents Structural changes in retinal blood vessels are critical biomarkers for the onset and progression of glaucoma and other ocular diseases. However, current vessel segmentation approaches largely rely on supervised learning and extensive manual annotations, which are costly, error-prone, and difficult to obtain in optical coherence tomography angiography. Here we present BioVessel-Net, an unsupervised generative framework that integrates vessel biostatistics with adversarial refinement and a radius-guided segmentation strategy. Unlike pixel-based methods, BioVessel-Net directly models vascular structures with biostatistical coherence, achieving accurate and explainable vessel extraction without labeled data or high-performance computing. To support training and evaluation, we introduce RetinaMix, a new benchmark dataset of 2D and 3D OCTA images with high-resolution vessel details from diverse populations. Experimental results demonstrate that BioVessel-Net achieves near-perfect segmentation accuracy across RetinaMix and existing datasets, substantially outperforming state-of-the-art supervised and semi-supervised methods. Together, BioVessel-Net and RetinaMix provide a label-free, computationally efficient, and clinically interpretable solution for retinal vessel analysis, with broad potential for glaucoma monitoring, blood flow modeling, and progression prediction. Code and dataset are available: https://github.com/VikiXie/SatMar8.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23617
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images
Huang, Cheng
Xie, Weizheng
Gao, Fan
Liu, Yutong
Wu, Ruoling
Han, Zeyu
Qiu, Jingxi
Wang, Xiangxiang
Yang, Zhenglin
Wang, Hao
Yu, Yongbin
Computer Vision and Pattern Recognition
Artificial Intelligence
Structural changes in retinal blood vessels are critical biomarkers for the onset and progression of glaucoma and other ocular diseases. However, current vessel segmentation approaches largely rely on supervised learning and extensive manual annotations, which are costly, error-prone, and difficult to obtain in optical coherence tomography angiography. Here we present BioVessel-Net, an unsupervised generative framework that integrates vessel biostatistics with adversarial refinement and a radius-guided segmentation strategy. Unlike pixel-based methods, BioVessel-Net directly models vascular structures with biostatistical coherence, achieving accurate and explainable vessel extraction without labeled data or high-performance computing. To support training and evaluation, we introduce RetinaMix, a new benchmark dataset of 2D and 3D OCTA images with high-resolution vessel details from diverse populations. Experimental results demonstrate that BioVessel-Net achieves near-perfect segmentation accuracy across RetinaMix and existing datasets, substantially outperforming state-of-the-art supervised and semi-supervised methods. Together, BioVessel-Net and RetinaMix provide a label-free, computationally efficient, and clinically interpretable solution for retinal vessel analysis, with broad potential for glaucoma monitoring, blood flow modeling, and progression prediction. Code and dataset are available: https://github.com/VikiXie/SatMar8.
title BioVessel-Net and RetinaMix: Unsupervised Retinal Vessel Segmentation from OCTA Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.23617