[1]Lü Jia,YANG Hongqiang.U-Net-based graph-structured auxiliary supervision network for retinal vessel segmentation[J].CAAI transactions on intelligent systems,2026,21(5):1166-1179.[doi:10.11992/tis.202509041]
Copy

U-Net-based graph-structured auxiliary supervision network for retinal vessel segmentation

CAAI transactions on intelligent systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 5 Page number: 1166-1179 Column: 学术论文—机器学习 Public date: 2026-09-05
Title:
U-Net-based graph-structured auxiliary supervision network for retinal vessel segmentation
Author(s):
Lü Jia1; 2;  YANG Hongqiang1
1. College of Computer and Information Sciences, Chongqing Normal University, Chongqing 401331, China;
2. National Center for Applied Mathematics in Chongqing, Chongqing 401331, China
Keywords:
retinal vessel segmentation; deep learning; U-Net; graph-structured auxiliary supervision; vessel skeleton; topological structure; multi-level feature fusion; connectivity
CLC:
TP391.4
DOI:
10.11992/tis.202509041
Abstract:
Existing deep learning-based retinal vessel segmentation methods, relying exclusively on pixel-wise mask supervision, encounter significant challenges in effectively modeling intricate branching patterns and overall global connectivity features, which leads to structural anomalies such as vascular discontinuities in the segmentation results. Thus, a U-Net-based graph-structured auxiliary supervision network for retinal vessel segmentation is presented in this paper. Firstly, using a vessel skeleton-guided structural encoding algorithm, key bifurcation points and connectivity relationships are transformed into structural supervision cues, enabling the network to capture the global structural attributes of retinal vessels. Secondly, to achieve effective integration of visual-semantic and topological structural features, a multi-level information flow attention fusion module is designed, enhancing the network’s structural representation capability. Finally, an auxiliary supervision mechanism is utilized to guide the network in jointly learning topological structural features and visual-semantic features, balancing segmentation accuracy with vessel morphological consistency. Evaluation on CHASEDB1, DRIVE and STARE datasets reveals that the proposed network achieves accurate retinal vessel segmentation, while effectively mitigates vascular discontinuities issues, thereby providing a reference for preserving biological consistency of segmentation outcomes.
References:
[1] SINGH C. Metabolism and vascular retinopathies: current perspectives and future directions[J]. Diagnostics, 2022, 12(4): 903
[2] LIU Xinghui, TAN Hongwen, WANG Wu, et al. Deep learning based retinal vessel segmentation and hypertensive retinopathy quantification using heterogeneous features cross-attention neural network[J]. Frontiers in medicine, 2024, 11: 1377479
[3] CHEN Shuli, XU Yi, CHEN Bo, et al. Remnant cholesterol is correlated with retinal vascular morphology and diabetic retinopathy in type 2 diabetes mellitus: a cross-sectional study[J]. Lipids in health and disease, 2024, 23(1): 75
[4] SUNG J Y, LEE K H, JUN J H, et al. Changes in peripapillary microvasculature in patients with type 2 diabetes patients: effect of systemic hypertension[J]. Scientific reports, 2023, 13: 19459
[5] 张菡, 贾红艳, 凌赛广, 等. 70岁以上冠心病患者基于人工智能的视网膜血管形态参数研究[J]. 眼科, 2024, 33(4): 285-289 ZHANG Han, JIA Hongyan, LING Saiguang, et al. Correlation analysis between retinal vascular morphology parameters and 70 years-old or over coronary heart disease based on artificial intelligence[J]. Ophthalmology in China, 2024, 33(4): 285-289
[6] 吕佳, 王泽宇. 基于深度学习的视网膜血管分割方法综述[J]. 重庆师范大学学报(自然科学版), 2024, 41(4): 110-125 L? Jia, WANG Zeyu. A survey of retinal vessel segmentation algorithms based on deep learning[J]. Journal of Chongqing Normal University (natural science), 2024, 41(4): 110-125
[7] 汪有崧, 裴峻鹏, 李增辉, 等. 深度学习的视网膜血管分割研究综述[J]. 计算机科学与探索, 2024, 18(8): 1960-1978 WANG Yousong, PEI Junpeng, LI Zenghui, et al. Review of research on deep learning in retinal blood vessel segmentation[J]. Journal of frontiers of computer science and technology, 2024, 18(8): 1960-1978
[8] LIU Li, QIANG Ma, OUYANG Cheng, et al. Topology optimization in medical image segmentation with fast Euler characteristic[EB/OL]. (2025-08-05)[2025-09-27]. https://doi.org/10.48550/arXiv.2507.23763.
[9] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[10] 缪林一, 李峰. 基于动态特征图卷积网络的视网膜血管分割方法[J]. 中国激光, 2024, 51(15): 181-191 MIAO Linyi, LI Feng. Retinal vessel segmentation based on dynamic feature graph convolutional network[J]. Chinese journal of lasers, 2024, 51(15): 181-191
[11] 吴晨玥, 易本顺, 章云港, 等. 基于改进卷积神经网络的视网膜血管图像分割[J]. 光学学报, 2018, 38(11): 125-131 WU Chenyue, YI Benshun, ZHANG Yungang, et al. Retinal vessel image segmentation based on improved convolutional neural network[J]. Acta optica sinica, 2018, 38(11): 125-131
[12] 易三莉, 陈建亭, 贺建峰. ASR-UNet: 一种基于注意力机制改进的视网膜血管分割算法[J]. 山东大学学报(理学版), 2021, 56(9): 13-20 YI Sanli, CHEN Jianting, HE Jianfeng. ASR-UNet: an improved retinal vessels segmentation algorithm based on attention mechanism[J]. Journal of Shandong University (natural science), 2021, 56(9): 13-20
[13] YI Yugen, GUO Changlu, HU Yangtao, et al. BCR-UNet: bi-directional ConvLSTM residual U-Net for retinal blood vessel segmentation[J]. Frontiers in public health, 2022, 10: 1056226
[14] JIA Wenran, MA Simin, GENG Peng, et al. DT-net: joint dual-input transformer and CNN for retinal vessel segmentation[J]. Computers, materials & continua, 2023, 76(3): 3393-3411.
[15] TONG Le, LI Tianjiu, ZHANG Qian, et al. LiViT-Net: a U-Net-like, lightweight Transformer network for retinal vessel segmentation[J]. Computational and structural biotechnology journal, 2024, 24: 213-224
[16] LI Daxiang, SU Miao, LIU Ying. MSPDD-net: Mamba semantic perception dual decoding network for retinal image vessel segmentation[J]. Computers in biology and medicine, 2025, 193: 110370
[17] 张蓉蓉, 吕晓琪, 李菁, 等. 双路径编码和跨级解耦的视网膜血管分割[J]. 光学精密工程, 2025, 33(14): 2242-2261 ZHANG Rongrong, L? Xiaoqi, LI Jing, et al. Dual-path encoding and cross-level decoupling for retinal vessel segmentation[J]. Optics and precision engineering, 2025, 33(14): 2242-2261
[18] 彭圆圆, 黎浩洋, 李文, 等. MFAL-Mamba: 多尺度特征聚合和注意力引导的眼底血管分割算法[J]. 光学学报, 2025, 45(22): 214-224 PENG Yuanyuan, LI Haoyang, LI Wen, et al. MFAL-mamba: fundus blood vessel segmentation algorithm based on multi-scale features and attention mechanism[J]. Acta optica sinica, 2025, 45(22): 214-224
[19] 王植炜, 黄梓航, 郭英杰, 等. 基于GAN的视网膜血管分割标签优化方法[J]. 华中科技大学学报(自然科学版), 2025, 53(9): 108-113 WANG Zhiwei, HUANG Zihang, GUO Yingjie, et al. GAN-based label refinement method for retinal vessel segmentation[J]. Journal of Huazhong University of Science and Technology (natural science edition), 2025, 53(9): 108-113
[20] HERNANDEZ R J, ROBERTS P A, EL-BOURI W K. Advancing treatment of retinal disease through in silico trials[J]. Progress in biomedical engineering, 2023, 5(2): 022002
[21] WANG Zeyu, JIA L V, LIANG Haocheng. Partial class activation mapping guided graph convolution cascaded U-Net for retinal vessel segmentation[J]. Computers in biology and medicine, 2024, 178: 108736
[22] ZENG Shuang, LEE C H, NNAMDI M C, et al. Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation[EB/OL]. (2025-05-06)[2025-09-27]. https://doi.org/10.48550/arXiv.2505.03896.
[23] SHIT S, PAETZOLD J C, SEKUBOYINA A, et al. clDice - a novel topology-preserving loss function for tubular structure segmentation[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 16555-16564.
[24] LUX L, BERGER A H, WEERS A, et al. Topograph: an efficient graph-based framework for strictly topology preserving image segmentation[EB/OL]. (2025-04-17)[2025-09-27]. https://doi.org/10.48550/arXiv.2411.03228.
[25] SCHACHT B, GREVING I, FRINTROP S, et al. ContextLoss: context information for topology-preserving segmentation[EB/OL]. (2025-06-10)[2025-09-27]. https://doi.org/10.48550/arXiv.2506.11134.
[26] ZHOU Yi, AHMED T S, WANG Meng, et al. Masked vascular structure segmentation and completion in retinal images[J]. IEEE transactions on medical imaging, 2025, 44(6): 2492-2503
[27] ZHANG T Y, SUEN C Y. A fast parallel algorithm for thinning digital patterns[J]. Communications of the ACM, 1984, 27(3): 236-239
[28] HE Songtao, BASTANI F, JAGWANI S, et al. Sat2Graph: road graph extraction through graph-tensor encoding[C]//Computer Vision–ECCV 2020. Cham: Springer, 2020: 51-67.
[29] AGUIAR M, CASTANO F, TRUJILLO M. Segmentation and detection of vascular bifurcations and crossings in retinal images[C]//Advances in Computing. Cham: Springer, 2018: 432-443.
[30] OWEN C G, RUDNICKA A R, NIGHTINGALE C M, et al. Retinal arteriolar tortuosity and cardiovascular risk factors in a multi-ethnic population study of 10-year-old children; the Child Heart and Health Study in England (CHASE)[J]. Arteriosclerosis, thrombosis, and vascular biology, 2011, 31(8): 1933-1938
[31] STAAL J, ABRAMOFF M D, NIEMEIJER M, et al. Ridge-based vessel segmentation in color images of the retina[J]. IEEE transactions on medical imaging, 2004, 23(4): 501-509
[32] HOOVER A D, KOUZNETSOVA V, GOLDBAUM M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response[J]. IEEE transactions on medical imaging, 2000, 19(3): 203-210
[33] HU Xiaoling, LI Fuxin, SAMARAS D, et al. Topology-preserving deep image segmentation[C]//Proceedings of the 33rd international conference on neural information processing systems. Red Hook: Curran Associates Inc. , 2019: 5657-5668.
[34] ZHOU Zongwei, RAHMAN SIDDIQUEE M M, TAJBAKHSH N, et al. UNet++: a nested U-Net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer, 2018: 3-11.
[35] OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-Net: learning where to look for the pancreas[EB/OL]. (2018-05-20)[2025-09-27]. https://doi.org/10.48550/arXiv.1804.03999.
[36] JHA D, SMEDSRUD P H, RIEGLER M A, et al. ResUNet++: an advanced architecture for medical image segmentation[C]//2019 IEEE International Symposium on Multimedia. San Diego: IEEE, 2019: 225-2255.
[37] LI Liangzhi, VERMA M, NAKASHIMA Y, et al. IterNet: retinal image segmentation utilizing structural redundancy in vessel networks[C]//2020 IEEE Winter Conference on Applications of Computer Vision. Snowmass: IEEE, 2020: 3645-3654.
Similar References:

Memo

-

Last Update: 2026-09-05

Copyright © CAAI Transactions on Intelligent Systems