Acta Optica Sinica, Volume. 40, Issue 9, 0910001(2020)

Retinal Blood Vessel Segmentation Based on Fuzzy C-Means Clustering According to the Local Line Structural Constraints

Hong Jia, Chujun Zheng*, Canbiao Li, Wenbin Wang, and Yanbing Xu
Author Affiliations
  • School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou, Guangdong 510006, China
  • show less
    Figures & Tables(11)
    Flowchart of the proposed method
    Images of the pre-processing results. (a) Color fundus image; (b) green channel; (c) morphological open operation of Fig. 2(b); (d) image enhancement of Fig. 2(c) by CLAHE
    Multi-scale match filter response images. (a) Response image with σ=1; (b) response image with σ=2; (c) response image with all scales
    Schematic diagram of B-COSFIRE. (a) Principle of B-COSFIRE; (b) symmetrical B-COSFIRE structure; (c) asymmetric B-COSFIRE structure
    Response image of B-COSFIRE filtering. (a) Color fundus image; (b) result of B-COSFIRE filtering
    Schematic diagram of line detector structure. (a) Line detector schematic diagram; (b) schematic diagram of line detector matched with vessel; (c) local neighborhood information
    Segmentation result images of the DRIVE database. (a) The best result of images; (b) the worst result of images; (c) segmentation result of 15th images; (d) segmentation result of 18th images
    Segmentation results of lesion image. (a) Segmentation result of K-means; (b) segmentation result of FCM; (c) segmentation result of proposed method
    Results of proposed method and FCM. (a) Results of FCM; (b) results of the proposed method; (c) segmentation images manually marked by expert
    • Table 1. Segmentation performance comparison of proposed method and FCM%

      View table

      Table 1. Segmentation performance comparison of proposed method and FCM%

      MethodAccSenSpe
      FCM94.0460.7798.98
      FCM_LLC94.2167.2198.20
      Difference0.176.44-0.78
    • Table 2. Performance of different retinal blood vessel segmentation methods%

      View table

      Table 2. Performance of different retinal blood vessel segmentation methods%

      MethodAverage AccAverage SenAverage Spe
      The 2nd observer94.7377.6397.25
      Chaudhuri et al[7]92.8461.6897.41
      Zana and Klein[9]93.7769.71
      Azzopardi et al[17]94.2775.2697.07
      Meng et.al[21]93.8358.1193.11
      Kande et al[15]89.11
      Cai et al[22]93.0077.0095.00
      Wang et al[23]93.8256.8699.26
      Proposed method94.2167.2198.20
    Tools

    Get Citation

    Copy Citation Text

    Hong Jia, Chujun Zheng, Canbiao Li, Wenbin Wang, Yanbing Xu. Retinal Blood Vessel Segmentation Based on Fuzzy C-Means Clustering According to the Local Line Structural Constraints[J]. Acta Optica Sinica, 2020, 40(9): 0910001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Nov. 29, 2019

    Accepted: Jan. 19, 2020

    Published Online: May. 6, 2020

    The Author Email: Chujun Zheng (cjzheng@scnu.edu.cn)

    DOI:10.3788/AOS202040.0910001

    Topics