Multimedia Tools and Applications

, Volume 49, Issue 3, pp 447–462 | Cite as

Segmentation of optic disc in retinal images using an improved gradient vector flow algorithm

  • Huiyu Zhou
  • Gerald Schaefer
  • Tangwei Liu
  • Faquan Lin


Image segmentation plays an important role in the analysis of retinal images as the extraction of the optic disk provides important cues for accurate diagnosis of various retinopathic diseases. In recent years, gradient vector flow (GVF) based algorithms have been used successfully to successfully segment a variety of medical imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods can lead to less accurate segmentation results in certain cases. In this paper, we propose the use of a new mean shift-based GVF segmentation algorithm that drives the internal/external energies towards the correct direction. The proposed method incorporates a mean shift operation within the standard GVF cost function to arrive at a more accurate segmentation. Experimental results on a large dataset of retinal images demonstrate that the presented method optimally detects the border of the optic disc.


Retinal image analysis Optic disc Segmentation Gradient vector flow 


  1. 1.
    Abdel-Ghafar R, Morris T, Ritchings T, Wood I (2004) Detection and characterisation of the optic disk in glaucoma and diabetic retinopathy. In: Medical image understanding and analysis conferenceGoogle Scholar
  2. 2.
    Balasubramanian S, Khanna S, Chadrasekaran V (2007) Localisation of optic disk using independent component analysis and modified structural similarity measure. In: IAPR conference on machine vision applications, pp 281–285Google Scholar
  3. 3.
    Barrett S, Naess E, Molvik T (2001) Employing the hough transform to locate the optic disk. Biomed Sci Instrum 37:81–86Google Scholar
  4. 4.
    Biswas P, Pandit M (2002) Opti-GVF snake model for face segmentation from video sequences. In: Proc. of the third Indian conference on computer vision, graphics & image processingGoogle Scholar
  5. 5.
    Bradski G (1998) Computer vision face tracking for use in a perceptual user interface. Intel Technology Journal 2nd quarterGoogle Scholar
  6. 6.
    Cheng Y (1995) Mean shift, mode seeking, and clustering. IEEE Trans Pattern Anal Mach Intell 17:790–799CrossRefGoogle Scholar
  7. 7.
    Comaniciu D, Ramesh V, Meer P (2000) Real-time tracking of non-rigid objects using mean shift. In: Proc. of IEEE conf. on computer vision and pattern recognition, pp 142–149Google Scholar
  8. 8.
    Herzog A, Boyer K, Roberts C (2005) Extracting the optic disk endpoints in optical coherence tomography data. In: IEEE workshop on applications of computer vision, vol 1, pp 263–268Google Scholar
  9. 9.
    Ikram M, Borger P, Assink J, Jonas J, A Hofman M, de Jong P (2002) Comparing ophthalmoscopy, slide viewing, and semiautomated systems in optic disc morphometry. Ophthalmology 109(3):486–493CrossRefGoogle Scholar
  10. 10.
    Infeld D, O’Shea J (1998) Diabetic retinopathy. Postgraduate Med J 74:129–133CrossRefGoogle Scholar
  11. 11.
    Kande G, Venkata Subbaiah P, Satya Savithri T (2008) Segmentation of exudates and optic disk in retinal images. In: Proc. of sixth Indian conference on computer vision, graphics & image processing, pp 535–542Google Scholar
  12. 12.
    Li C, Liu J, Fox M (2005) Segmentation of edge preserving gradient vector flow: an approach toward automatically initializing and splitting of snakes. In: IEEE conf. on comput. vis. patter. rec., pp 162–167Google Scholar
  13. 13.
    Li H, Chutatape O (2001) Automatic location of optic disk in retinal images. In: Proc. of international conference on image processing, pp 837–840Google Scholar
  14. 14.
    Liu T, Zhou H, Lin F, Pang Y, Wu J (2008) Improving image segmentation by gradient vector flow and mean shift. Pattern Recogn Lett 29(1):90–95CrossRefGoogle Scholar
  15. 15.
    Mahfouz A, Fahmy A (2009) Ultrafast localization of the optic disc using dimensionality reduction of the search space. In: Medical image computing and computer-assisted intervention, pp 985–992Google Scholar
  16. 16.
    Mayer-Base A (2004) Pattern recognition for medical imaging. Elsevier, AmsterdamGoogle Scholar
  17. 17.
    Mendels F, Heneghan C, Thiran JP (1999) Identification of the optic disk boundary in retinal images using active contours. In: Proc. of the Irish machine vision and image processing conference, pp 103–115Google Scholar
  18. 18.
    Osareh A, Mirmehdi M, Thomas B, Markham R (2002) Comparison of colour spaces for optic disc localisation in retinal images. In: Proc. of international conference on pattern recognition, pp 743–746Google Scholar
  19. 19.
    Pallawala P, Hsu W, Lee ML, Eong KGA (2004) Automated optic disc localization and contour detection using ellipse fitting and wavelet transform. In: European conference on computer vision, pp 139–151Google Scholar
  20. 20.
    Paragios N, Deriche R (2002) Geodesic active regions and level set methods for supervised texture segmentation. Int J Comput Vis 46:223–247MATHCrossRefGoogle Scholar
  21. 21.
    Patton N, Aslam T, MacGillivray T, Deary I, Dhillon B, Eikelboom R, Yogesan K, Constable I (2006) Retinal image analysis: concepts, applications and potential. Prog Retin Eye Res 25:99–127CrossRefGoogle Scholar
  22. 22.
    Rigo W, Silva AD, Rauber T (2002) Semi-automatic identification of optic disk by image processing for quantitative funduscopy. In: Computer graphics and image processing. Brazilian Symposium, p 18Google Scholar
  23. 23.
    Riordan-Eva P, Whitcher J (2007) Vaughan & Asbury’s genneral ophthalmology, 17th edn. McGraw-Hill, New YorkGoogle Scholar
  24. 24.
    Siddalingaswamy P, Prabhu K (2009) Automated detection of optic disc and exudates in retinal images. In: 13th international conference on biomedical engineering, pp 277–279Google Scholar
  25. 25.
    Sinthanayothin C, Boyce J, Cook H, Williamson T (2008) Automated location of the optic disk in retinal images. J Biomed Sci Eng 2:90–95Google Scholar
  26. 26.
    Soares J, Leandro J, Cesar R, Jelinek H, Cree M (2006) Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans Med Imag 25(9):1214–1222CrossRefGoogle Scholar
  27. 27.
    Staal J, Niemeijer A, Viergever M, van Ginneken B (2004) Ridge based vessel segmentation in color images of the retina. IEEE Trans Med Imag 23:501–509CrossRefGoogle Scholar
  28. 28.
    ter Haar F (2005) Automatic localization of the optic disc in digital colour images of the human retina. Master’s thesis, Utrecht University, NetherlandsGoogle Scholar
  29. 29.
    Tobin K, Chaum E, Govindasamy V, Karnowski T (2007) Detection of anatomic structures in human retinal imagery. IEEE Trans Med Imag 26(12):1729–1739CrossRefGoogle Scholar
  30. 30.
    Wang J, Thiesson B, Xu Y, Cohen M (2004) Image and video segmentation by anisotropic kernel mean shift. In: Proc. of European conference on computer vision, pp 238–249Google Scholar
  31. 31.
    Witkin A, DTerzopoulos, Kass M (1987) Signal matching through scale space. Int J Comput Vis 1(2):133–144CrossRefGoogle Scholar
  32. 32.
    Xu C, Prince J (1997) Gradient vector flow: A new external force for snakes. In: Proc. of IEEE conf. computer vision and pattern recognition, pp 66–71Google Scholar
  33. 33.
    Xu C, Prince J (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359–369MATHCrossRefMathSciNetGoogle Scholar
  34. 34.
    Xu J, Chutatape O, Sung E, Zheng C, Kuan P (2007) Optic disk feature extraction via modified deformable model technique for glaucoma analysis. Pattern Recogn 40(7):2063–2076MATHCrossRefGoogle Scholar
  35. 35.
    Xu N, Ahuja N, Bansal R (2007) Object segmentation using graph cuts based active contours. Comput Vis Image Underst 107(3):210–224CrossRefGoogle Scholar
  36. 36.
    Zhou H, Liu T, Hu H, Pang Y, Lin F, Wu J (2005) A hybrid framework for image segmentation. In: Proc. of IEEE international conference on acoustics, speech, and signal processing, pp 749–752Google Scholar
  37. 37.
    Zhu G, Zeng Q, Wang C (2006) Dual geometric active contour for image segmentation. Opt Eng 45(8):080,505Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Huiyu Zhou
    • 1
  • Gerald Schaefer
    • 2
  • Tangwei Liu
    • 3
  • Faquan Lin
    • 3
  1. 1.The Institute of Electronics, Communications and Information Technology (ECIT)Queen’s University BelfastBelfastUK
  2. 2.Department of Computer ScienceLoughborough UniversityLoughboroughUK
  3. 3.Guangxi Medical UniversityNanningPeoples’ Republic of China

Personalised recommendations