Advertisement

Blood Vessels Segmentation of Retinal Fundus Image via wStack-Based Object-Oriented Region Growing

  • Ahmad Firdaus Ahmad FadzilEmail author
  • Shafaf Ibrahim
  • Noor Elaiza Abd Khalid
Conference paper

Abstract

Retinal fundus image is an important medical imaging modality that provide different information on eye diseases. Eye disease such as glaucoma can be diagnosed by evaluating different features of retinal fundus images such as optic disc, macula, and blood vessels. Various image segmentation algorithm has been employed to segment blood vessels features of retinal fundus image as it is the hardest feature to segment compare to optic disc and macula. Region growing segmentation algorithm is one of the segmentation algorithm that is proven to be able to segment various type of medical imaging modalities. However, region growing segmentation algorithm has massive caveats especially in dealing with memory stacks, and restricted flexibility due to its recursive programming nature. In this paper, a segmentation algorithm that utilizes stack-based object-oriented region growing (SORG) algorithm is proposed. This algorithm proposes the combination of stack data structure and object-oriented programming paradigm in order to negate the utilization of recursive programming. The result shows that SORG able to provide decent segmentation when assessed in terms of accuracy when being evaluated with 30 manually annotated images

Keywords

Retinal fundus image Segmentation Region growing algorithm . stack-based. object-oriented 

References

  1. 1.
    Mary, M.C.V.S., Rajsingh, E.B., Naik, G.R.: Retinal fundus image analysis for diagnosis of glaucoma: a comprehensive survey. IEEE Access 4, 4327–4354 (2016)CrossRefGoogle Scholar
  2. 2.
    Odstrcilik, J., Kolar, R., Budai, A., Hornegger, J., Jan, J., Gazarek, J., Angelopoulou, E.: Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database. IET Image Process. 7(4), 373–383 (2013)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Staal, J., Abràmoff, M.D., Niemeijer, M., Viergever, M.A., Van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501–509 (2004)CrossRefGoogle Scholar
  4. 4.
    Kayal, D., Banerjee, S.: A new dynamic thresholding based technique for detection of hard exudates in digital retinal fundus image. In: 2014 International Conference on Signal Processing and Integrated Networks (SPIN), pp. 141–144. IEEE (2014)Google Scholar
  5. 5.
    Usman, A., Khitran, S.A., Akram, M.U., Nadeem, Y.: A robust algorithm for optic disc segmentation from colored fundus images. In: International Conference Image Analysis and Recognition, pp. 303–310. Springer, Cham (2014)Google Scholar
  6. 6.
    Ye, C.F., Li, Y.Z., Zeng, W.Q.: Study of non-recursive transformation algorithms of recursive problems. In: Applied Mechanics and Materials, vol. 644, pp. 1969–1971. Trans Tech Publications (2014)Google Scholar
  7. 7.
    Hore, S., Chakraborty, S., Chatterjee, S., Dey, N., Ashour, A.S., Van Chung, L., Le, D.N.: An integrated interactive technique for image segmentation using stack based seeded 3. Region growing and thresholding. Int. J. Electrical Comput. Eng. 6(6), 2773 (2016)Google Scholar
  8. 8.
    Khalid, N.E.A., Ibrahim, S., Manaf, M., Ngah, U.K.: Seed-based region growing study for brain abnormalities segmentation. In: 2010 International Symposium on Information Technology (ITSim), vol. 2, pp. 856–860. IEEE (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Ahmad Firdaus Ahmad Fadzil
    • 1
    Email author
  • Shafaf Ibrahim
    • 1
  • Noor Elaiza Abd Khalid
    • 2
  1. 1.FSKM, Universiti Teknologi MARA Kampus JasinJasinMalaysia
  2. 2.FSKM, Universiti Teknologi MARA Kampus Shah AlamShah AlamMalaysia

Personalised recommendations