
浏览全部资源
扫码关注微信
宁夏大学 电子与电气工程学院, 宁夏 银川 750021
常汇谈,男,硕士研究生,2022年于河南大学获得学士学位,主要从事图像处理和深度学习方面的研究。E-mail:changht_321@163.com
马瑜,男,博士,教授,2013年于西北工业大学获得博士学位,主要从事计算机视觉和模式识别方面的研究。E-mail:mayu95@163.com
收稿:2026-06-10,
修回:2026-06-22,
纸质出版:2026-07-06
移动端阅览
常汇谈, 马瑜, 黄守彤, 等. 基于小波与粗概率先验双分支的眼底微细血管分割网络[J]. 液晶与显示, 2026,41(7):981-994.
CHANG Huitan, MA Yu, HUANG Shoutong, et al. Retinal micro-vessel segmentation based on wavelet and coarse probability prior dual-branch network[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(7): 981-994.
常汇谈, 马瑜, 黄守彤, 等. 基于小波与粗概率先验双分支的眼底微细血管分割网络[J]. 液晶与显示, 2026,41(7):981-994. DOI: 10.37188/CJLCD.2026-0107. CSTR: 32172.14.CJLCD.2026-0107.
CHANG Huitan, MA Yu, HUANG Shoutong, et al. Retinal micro-vessel segmentation based on wavelet and coarse probability prior dual-branch network[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(7): 981-994. DOI: 10.37188/CJLCD.2026-0107. CSTR: 32172.14.CJLCD.2026-0107.
视网膜血管的管径、分叉数等形态参数可作为临床诊疗的重要依据,精准分割微细血管对相关疾病的早期诊断至关重要。现有方法在微细血管检测中易出现血管拓扑断裂的现象,同时普遍存在粗细血管特征融合不充分的缺陷。本文采用IterMiUnet作为粗分割分支提取全局血管特征,Haar小波先验增强细血管频域表达能力,强化边缘细节特征。针对粗分割难以精准识别弱边界、伪影干扰等难分割区域的问题,以粗分割概率不确定性像素作为先验引导,使细血管分割模型主动聚焦上述难分割区域,进一步提升分割精度;构建双尺度概率编码融合机制,结合温度缩放与背景抑制策略,借助细血管分割结果优化粗分割输出,实现两类结果的自适应融合。在DRIVE、CHASE_DB1、STARE三个公开数据集上的实验结果表明,本文算法的分割性能优于当前多种主流方法,F1指标分别达到了0.825 7、0.836 0、0.835 7。本文算法整体分割效果稳定可靠,分割精度优良,能有效捕捉细血管细节并保持血管拓扑完整性。
Morphological parameters such as the diameter and bifurcation of retinal blood vessels serve as important references for clinical diagnosis, and accurate segmentation of microvessels is essential for the early diagnosis of related diseases. Existing segmentation methods often suffer from blurred edges, fractured topological structures, and inadequate fusion of thick and thin vessel features in microvessel detection.To address these issues, this paper proposes a dual-branch segmentation network. We adopt IterMiUnet as the coarse segmentation branch to extract global vascular features, and introduce Haar wavelet prior to enhance the frequency-domain representation and edge details of microvessels. Since coarse segmentation struggles to identify weak boundaries and fractured vessels accurately, we take uncertain pixels from coarse segmentation probability as prior guidance, enabling the fine segmentation model to focus on these challenging regions and boost segmentation precision.A dual-scale probability encoding fusion mechanism combined with temperature scaling and background suppression is also constructed. The outputs of coarse segmentation are optimized using fine segmentation results to realize adaptive fusion and reduce background interference. Experiments on DRIVE, CHASE_DB1 and STARE datasets demonstrate that the proposed algorithm outperforms mainstream methods, with F1 scores of 0.825 7, 0.836 0 and 0.835 7 respectively. It achieves stable and reliable performance, and can effectively capture microvascular details while maintaining the topological integrity of blood vessels.
DAS S , CHAKRABORTY S , MISHRA M , et al . Assessment of retinal blood vessel segmentation using U-Net model: A deep learning approach [J]. Franklin Open , 2024 , 8 : 100143 . doi: 10.1016/j.fraope.2024.100143 http://dx.doi.org/10.1016/j.fraope.2024.100143
SONI T , GUPTA S , KUMAR K S . Exploring retinal vessel segmentation: deep learning models and their applications [C]. 2025 3rd International Conference on Advancement in Computation & Computer Technologies (InCACCT) . Gharuan : IEEE , 2025 : 715 - 719 .
张光华 , 杨阳 , 徐国华 . 无源多领域自适应糖尿病视网膜病变分类方法 [J]. 液晶与显示 , 2025 , 40 ( 7 ): 1080 - 1091 . doi: 10.37188/cjlcd.2025-0024 http://dx.doi.org/10.37188/cjlcd.2025-0024
ZHANG G H , YANG Y , XU G H . Unsupervised source-free multi-domain adaptive diabetic retinopathy classification [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 7 ): 1080 - 1091 . doi: 10.37188/cjlcd.2025-0024 http://dx.doi.org/10.37188/cjlcd.2025-0024
范琳琳 , 程韵 , 田晓冰 . 基于匹配滤波和形态学处理的视网膜血管分割 [J]. 电脑知识与技术 , 2019 , 15 ( 17 ): 188 - 190 .
FAN L L , CHENG Y , TIAN X B . Retinal blood vessel segmentation based on matched filtering and morphological processing [J]. Computer Knowledge and Technology , 2019 , 15 ( 17 ): 188 - 190 . (in Chinese)
WANG S , PAN J L , ZHANG X , et al . Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy [J]. Light: Science & Applications , 2024 , 13 ( 1 ): 254 .
LUO M C , JIANG M R , SHASTRI B J , et al . Highly scalable machine vision enabled with meta-optics-based ultra-wide neural network [J]. eLight , 2026 , 6 ( 1 ): 10 . doi: 10.1186/s43593-026-00127-y http://dx.doi.org/10.1186/s43593-026-00127-y
SHELHAMER E , LONG J , DARRELL T . Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 4 ): 640 - 651 . doi: 10.1109/tpami.2016.2572683 http://dx.doi.org/10.1109/tpami.2016.2572683
RONNEBERGER O , FISCHER P , BROX T . U-Net: convolutional networks for biomedical image segmentation [C]. 18th International Conference on Medical Image Computing and Computer-Assisted Intervention . Munich : Springer , 2015 : 234 - 241 . doi: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28
CHEN G P , LI L , DAI Y , et al . AAU-Net: an adaptive attention U-net for breast lesions segmentation in ultrasound images [J]. IEEE Transactions on Medical Imaging , 2023 , 42 ( 5 ): 1289 - 1300 .
郭昊虎 , 高若谦 , 葛明锋 , 等 . 基于特征图金字塔的冠脉造影图像血管分割方法 [J]. 中国光学(中英文) , 2024 , 17 ( 4 ): 971 - 981 . doi: 10.37188/co.2023-0186 http://dx.doi.org/10.37188/co.2023-0186
GUO H H , GAO R Q , GE M F , et al . Coronary artery angiography image vessel segmentation method based on feature pyramid network [J]. Chinese Optics , 2024 , 17 ( 4 ): 971 - 981 . doi: 10.37188/co.2023-0186 http://dx.doi.org/10.37188/co.2023-0186
LIU Y H , SHEN J , ZHAI C X , et al . A retinal vessel segmentation network with dual-stage network and vessel pixel emendation [J]. IEEE Transactions on Instrumentation and Measurement , 2025 , 74 : 2501117 . doi: 10.1109/tim.2024.3500060 http://dx.doi.org/10.1109/tim.2024.3500060
QU Z W , ZHUO L , CAO J , et al . TP-Net: two-path network for retinal vessel segmentation [J]. IEEE Journal of Biomedical and Health Informatics , 2023 , 27 ( 4 ): 1979 - 1990 . doi: 10.1109/jbhi.2023.3237704 http://dx.doi.org/10.1109/jbhi.2023.3237704
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 . doi: 10.37188/ope.20253314.2242 http://dx.doi.org/10.37188/ope.20253314.2242
ZHANG R R , LÜ X Q , LI J , et al . Dual-path encoding and cross-level decoupling for retinal vessel segmentation [J]. Optics and Precision Engineering , 2025 , 33 ( 14 ): 2242 - 2261 . doi: 10.37188/ope.20253314.2242 http://dx.doi.org/10.37188/ope.20253314.2242
WANG C C , WANG Y F , XU Q , et al . WaveRNet: Wavelet-guided frequency learning for multi-source domain-generalized retinal vessel segmentation [J/OL]. arXiv , 2026 : 2601 . 05942 . doi: 10.1007/978-981-92-3378-6_43 http://dx.doi.org/10.1007/978-981-92-3378-6_43
LI X L , ZHOU H . WDM-UNet: A wavelet-deformable gated fusion network for multi-scale retinal vessel segmentation [J]. Sensors , 2025 , 25 ( 15 ): 4840 . doi: 10.3390/s25154840 http://dx.doi.org/10.3390/s25154840
KUMAR A , AGRAWAL R K , JOSEPH L . IterMiUnet: a lightweight architecture for automatic blood vessel segmentation [J]. Multimedia Tools and Applications , 2023 , 82 ( 28 ): 43207 - 43231 . doi: 10.1007/s11042-023-15433-7 http://dx.doi.org/10.1007/s11042-023-15433-7
DUTTA P , MITRA S , ROY S K . Wavelet-infused convolution-transformer for efficient segmentation in medical images [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2025 , 55 ( 5 ): 3326 - 3337 . doi: 10.1109/tsmc.2025.3539573 http://dx.doi.org/10.1109/tsmc.2025.3539573
LIANG M , HAO J H , HOU H H , et al . WMFU-net: multi-scale wavelet mamba network and adaptive fusion for retinal vessel segmentation [J]. Biomedical Signal Processing and Control , 2026 , 121 : 110295 . doi: 10.1016/j.bspc.2026.110295 http://dx.doi.org/10.1016/j.bspc.2026.110295
LI L Z , 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 (WACV). Snowmass : IEEE , 2020 : 3645 - 3654 . doi: 10.1109/wacv45572.2020.9093621 http://dx.doi.org/10.1109/wacv45572.2020.9093621
HU J T , LIAO K , DINÇ N U , et al . Subwavelength imaging using a solid-immersion diffractive optical processor [J]. eLight , 2024 , 4 ( 1 ): 8 . doi: 10.1186/s43593-024-00067-5 http://dx.doi.org/10.1186/s43593-024-00067-5
SZEGEDY C , VANHOUCKE V , IOFFE S , et al . Rethinking the inception architecture for computer vision [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas : IEEE , 2016 : 2818 - 2826 . doi: 10.1109/cvpr.2016.308 http://dx.doi.org/10.1109/cvpr.2016.308
GUO C , PLEISS G , SUN Y , et al . On calibration of modern neural networks [C]// Proceedings of the 34th International Conference on Machine Learning . Sydney : PMLR , 2017 : 1321 - 1330 .
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 . doi: 10.1109/tmi.2004.825627 http://dx.doi.org/10.1109/tmi.2004.825627
OWEN C G , RUDNICKA A R , MULLEN R , et al . Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (CAIAR) program [J]. Investigative Opthalmology & Visual Science , 2009 , 50 ( 5 ): 2004 . doi: 10.1167/iovs.08-3018 http://dx.doi.org/10.1167/iovs.08-3018
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 . doi: 10.1109/42.845178 http://dx.doi.org/10.1109/42.845178
FABBRI R , DA F . COSTA L, TORELLI J C, et al. 2D Euclidean distance transform algorithms: a comparative survey [J]. ACM Computing Surveys , 2008 , 40 ( 1 ): 2 . doi: 10.1145/1322432.1322434 http://dx.doi.org/10.1145/1322432.1322434
巫志辉 , 王立忠 , 梁晋 , 等 . 面向机械零件三角网格模型自动配准中增强特征的分割方法 [J]. 中国光学(中英文) , 2024 , 17 ( 5 ): 1112 - 1124 . doi: 10.37188/co.2023-0225 http://dx.doi.org/10.37188/co.2023-0225
WU Z H , WANG L Z , LIANG J , et al . Segmentation method for enhanced features in automatic registration of triangular mesh model of mechanical parts [J]. Chinese Optics , 2024 , 17 ( 5 ): 1112 - 1124 . doi: 10.37188/co.2023-0225 http://dx.doi.org/10.37188/co.2023-0225
张书赫 , 曹良才 . 基于数字衍射的单幅眼底图像增强 [J]. 光学 精密工程 , 2024 , 32 ( 15 ): 2429 - 2438 . doi: 10.37188/ope.20243215.2429 http://dx.doi.org/10.37188/ope.20243215.2429
ZHANG S H , CAO L C . Digital diffraction method for single retinal image enhancement [J]. Optics and Precision Engineering , 2024 , 32 ( 15 ): 2429 - 2438 . doi: 10.37188/ope.20243215.2429 http://dx.doi.org/10.37188/ope.20243215.2429
LV N Z , XU L , CHEN Y L , et al . TCDDU-Net: combining transformer and convolutional dual-path decoding U-Net for retinal vessel segmentation [J]. Scientific Reports , 2024 , 14 ( 1 ): 25978 . doi: 10.1038/s41598-024-77464-w http://dx.doi.org/10.1038/s41598-024-77464-w
盖俊帅 , 马玉婷 , 张运海 , 等 . 用于眼底视网膜图像的去雾状杂散光算法 [J]. 液晶与显示 , 2024 , 39 ( 8 ): 1070 - 1078 .
GAI J S , MA Y T , ZHANG Y H , et al . Dehazing stray light algorithm for fundus retinal image [J]. Chinese Journal of Liquid Crystals and Displays , 2024 , 39 ( 8 ): 1070 - 1078 .
ZHOU Y P , CHANG H Y , LU X L , et al . DenseUNet: improved image classification method using standard convolution and dense transposed convolution [J]. Knowledge-Based Systems , 2022 , 254 : 109658 . doi: 10.1016/j.knosys.2022.109658 http://dx.doi.org/10.1016/j.knosys.2022.109658
LI J Y , GAO G , YANG L , et al . A retinal vessel segmentation network with multiple-dimension attention and adaptive feature fusion [J]. Computers in Biology and Medicine , 2024 , 172 : 108315 . doi: 10.1016/j.compbiomed.2024.108315 http://dx.doi.org/10.1016/j.compbiomed.2024.108315
RAHMAN M M , MARCULESCU R . MK-UNet: multi-kernel lightweight CNN for medical image segmentation [C]// 2025 IEEE/CVF International Conference on Computer Vision Workshops . Honolulu : IEEE , 2025 : 1053 - 1062 . doi: 10.1109/iccvw69036.2025.00114 http://dx.doi.org/10.1109/iccvw69036.2025.00114
0
浏览量
168
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621