A multi-scale global attention network for blood vessel segmentation from fundus images

被引:11
|
作者
Gao, Ge [1 ,2 ]
Li, Jianyong [3 ]
Yang, Lei [1 ,2 ]
Liu, Yanhong [1 ,2 ]
机构
[1] Zhengzhou Univ, Sch Elect & Informat Engn, Zhengzhou 450001, Henan, Peoples R China
[2] Robot Percept & Control Engn Lab, Zhengzhou 450001, Henan, Peoples R China
[3] Zhengzhou Univ Light Ind, Coll Comp & Commun Engn, Zhengzhou 450001, Peoples R China
基金
中国国家自然科学基金;
关键词
Retinal vessels segmentation; Deep learning; U-Net network; Global context attention; RETINAL IMAGES; NET;
D O I
10.1016/j.measurement.2023.113553
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Accurate segmentation of retinal fundus vessel images is vital to clinical diagnosis. Due to the intricate vascular morphology, high noise and low contrast of fundus vessel images, retinal fundus vessel segmentation is still a challenging task, especially for thin vessel segmentation. In recent years, on account of strong context feature extraction ability of deep learning, it has shown a remarkable performance in the automatic segmentation of retinal fundus vessels. However, it still exhibits certain limitations, such as information loss on micro objects or details, inadequate treatment of local features, etc. Faced with these challenging factors, we present a new multi-scale global attention network (MGA-Net). To realize effective feature representation, a dense attention U-Net network is proposed. Meanwhile, we design a global context attention (GCA) block to realize multi-scale feature fusion, allowing the global features from the deep network layers to flow to the shallow network layers. Further, aimed at retinal fundus vessel segmentation task again the class imbalance issue, the AG block is also introduced. Related experiments are conducted on CHASE_DB1, DRIVE and STARE datasets to show the effectiveness of proposed segmentation model. The experimental results demonstrate the robustness of the proposed method with Ft exceeding 82% on all three datasets and effectively improve the segmentation performance of thin vessels. The source code of proposed MGA-Net is available at https://github.com/gegao310/workspace.git.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Blood Vessel Segmentation in Eye Fundus Images
    Savu, Madalina
    Popescu, Dan
    Ichim, Loretta
    PROCEEDINGS OF 2017 INTERNATIONAL CONFERENCE ON SMART SYSTEMS AND TECHNOLOGIES (SST), 2017, : 245 - 249
  • [22] Customizing CNNs for Blood Vessel Segmentation From Fundus Images
    Vengalil, Sunil Kumar
    Sinha, Neelam
    Kruthiventi, Srinivas S. S.
    Babu, R. Venkatesh
    2016 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS (SPCOM), 2016,
  • [23] Gabor-net with multi-scale hierarchical fusion of features for fundus retinal blood vessel segmentation
    Fang, Tao
    Cai, Zhefei
    Fan, Yingle
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2024, 44 (02) : 402 - 413
  • [24] Skeleton-guided multi-scale dual-coordinate attention aggregation network for retinal blood vessel segmentation
    Zhou, Wei
    Wang, Xiaorui
    Yang, Xuekun
    Hu, Yangtao
    Yi, Yugen
    Computers in Biology and Medicine, 2024, 181
  • [25] A Multi-Scale Channel Attention Network for Prostate Segmentation
    Ding, Meiwen
    Lin, Zhiping
    Lee, Chau Hung
    Tan, Cher Heng
    Huang, Weimin
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2023, 70 (05) : 1754 - 1758
  • [26] Multi-scale attention network for segmentation of electron dense deposits in glomerular microscopic images
    Yang, Jinyue
    Hu, Xiuxiu
    Pan, Hong
    Chen, Pingsheng
    Xia, Siyu
    MICROSCOPY RESEARCH AND TECHNIQUE, 2022, 85 (09) : 3256 - 3264
  • [27] UNet segmentation network of COVID-19 CT images with multi-scale attention
    Chen, Mingju
    Yi, Sihang
    Yang, Mei
    Yang, Zhiwen
    Zhang, Xingyue
    MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2023, 20 (09) : 16762 - 16785
  • [28] Attention to fine-grained information: hierarchical multi-scale network for retinal vessel segmentation
    Chengzhi Lyu
    Guoqing Hu
    Dan Wang
    The Visual Computer, 2022, 38 : 345 - 355
  • [29] Res2Unet: A multi-scale channel attention network for retinal vessel segmentation
    Li, Xuejian
    Ding, Jiaqi
    Tang, Jijun
    Guo, Fei
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (14): : 12001 - 12015
  • [30] Attention to fine-grained information: hierarchical multi-scale network for retinal vessel segmentation
    Lyu, Chengzhi
    Hu, Guoqing
    Wang, Dan
    VISUAL COMPUTER, 2022, 38 (01): : 345 - 355