Medical & Biological Engineering & Computing

, Volume 49, Issue 6, pp 693–700

Analysis of retinal fundus images for grading of diabetic retinopathy severity

  • M. H. Ahmad Fadzil
  • Lila Iznita Izhar
  • Hermawan Nugroho
  • Hanung Adi Nugroho
Original Article

Abstract

Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina. In this article, a computerised DR grading system, which digitally analyses retinal fundus image, is used to measure foveal avascular zone. A v-fold cross-validation method is applied to the FINDeRS database to evaluate the performance of the DR system. It is shown that the system achieved sensitivity of >84%, specificity of >97% and accuracy of >95% for all DR stages. At high values of sensitivity (>95%), specificity (>97%) and accuracy (>98%) obtained for No DR and severe NPDR/PDR stages, the computerised DR grading system is suitable for early detection of DR and for effective treatment of severe cases.

Keywords

Diabetic retinopathy grading Foveal avascular zone Medical image analysis Retinal fundus images 

References

  1. 1.
    Ahmad Fadzil MH, Izhar LI (2008) A non-Invasive method for analysing the retina for ocular manifested diseases. Patent filing no. PI20083503 September, 2008 ed. Malaysia, v. patent filing no. PI20083503 September, 2008Google Scholar
  2. 2.
    Ahmad Fadzil MH, Lila Iznita I (2009) A non-Invasive method for analysing the retina for ocular manifested diseases. Patent filing no. PCT/MY2009/000025 2009 ed. Malaysia, v. patent filing no. PCT/MY2009/000025 2009Google Scholar
  3. 3.
    Ahmad Fadzil MH, Lila Iznita I (2009) An apparatus for monitoring and grading diabetic retinopathy. Patent filing no. PI20091936 May, 2009 ed. Malaysia, v. patent filing no. PI20091936 May, 2009Google Scholar
  4. 4.
    Ahmad Fadzil MH, Nugroho HA, Venkatachalam PA, et al (2008) Determination of retinal pigments from fundus images using independent component analysis. In: Proceeding of biomed 2008 4th Kuala Lumpur international conference on biomedical engineering vol 21. Springer, Berlin Heidelberg, 2008Google Scholar
  5. 5.
    Ahmad Fadzil MH, Nugroho HA (2009) Retinal vasculature enhancement using independent component analysis. J Biomed Sci Eng 2:543–549CrossRefGoogle Scholar
  6. 6.
    Ahmad Fadzil MH, Izhar LI, Venkatachalam PA, Karunakar TVN (2007) Extraction and reconstruction of retinal vasculature. J Med Eng Tech 31:435–442CrossRefGoogle Scholar
  7. 7.
    Ahmad Fadzil MH, Lila Iznita I, Nugroho HA (2009) Analysis of foveal avascular zone in color fundus image for grading of diabetic retinopathy. Int J Recent Trends Eng 2:101–104Google Scholar
  8. 8.
    American academy of ophthalmology retina panel. Preferred practice pattern guidelines. Diabetic retinopathy. American Academy of Ophthalmology San Francisco, CA. http://www.aao.org/ppp
  9. 9.
    Bradley A, Applegate RA, Zeffren BS, Heuven WAJ (1992) Psychophysical measurement of the size and shape of the human foveal avascular zone. Ophthal Physiol Opt 12:18–23CrossRefGoogle Scholar
  10. 10.
    Bresnick GH, Condit R, Syrjala S et al (1984) Abnormalities of the foveal avascular zone in diabetic retinopathy. Arch Ophthalmol 102:1286–1293PubMedGoogle Scholar
  11. 11.
    Comon P (1994) Independent component analysis, a new concept? Signal Process 36:287CrossRefGoogle Scholar
  12. 12.
    Conrath J, Giorgi R, Raccah D, Ridings B (2004) Foveal avascular zone in diabetic retinopathy: quantitative vs qualitative assessment. Eye 19:322–326CrossRefGoogle Scholar
  13. 13.
    Conrath J, Valat O, Giorgi R et al (2006) Semi-automated detection of the foveal avascular zone in fluorescein angiograms in diabetes mellitus. Clin Exp Ophthalmol 34:119–123CrossRefGoogle Scholar
  14. 14.
    Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New YorkGoogle Scholar
  15. 15.
    Fadzil MHA, Lila Iznita I, Hanung Adi N (2010) Determination of foveal avascular zone in diabetic retinopathy digital fundus images. Comput Biol Med 40:657–664CrossRefGoogle Scholar
  16. 16.
    Goh PP (2008) Status of diabetic retinopathy among diabetics registered to the diabetic eye registry, National eye database, 2007. Med J Malaysia 63:24–28PubMedGoogle Scholar
  17. 17.
    Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36PubMedGoogle Scholar
  18. 18.
    Hyvarinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Networks 13:411PubMedCrossRefGoogle Scholar
  19. 19.
    Izenman AJ (2008) Modern multivariate statistical techniques: regression, classification, and manifold learning. Springer New York, BerlinGoogle Scholar
  20. 20.
    Iznita L (2006) Analysis of retinal vasculature and foveal avascular zone for grading of diabetic retinopathy. M.Sc. Thesis, Universiti Teknologi PETRONAS, Electrical and electronics engineering programme. Bandar Seri Iskandar, Malaysia Google Scholar
  21. 21.
    Jelinek HF, Cree MJ, Leandro JJG et al (2007) Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy. J Opt Soc Am A 24:1448–1456CrossRefGoogle Scholar
  22. 22.
    John D, Braganza A, Kuriakose T (2006) A study of the foveal avascular zone using the Heidelberg retina angiogram-2 in normal eyes. In: Proceedings 34th all India optometry conference (AIOC 2008) Amritsar, India Google Scholar
  23. 23.
    Kahai P, Namuduri KR, Thompson H (2004) Decision support for automated screening of diabetic retinopathy. Conference on signals, systems and computers, vol 2. Conference record of the thirty-eighth asilomar Google Scholar
  24. 24.
    Kahai P, Namuduri KR, Thompson H (2006) A decision support framework for automated screening of diabetic retinopathy. Int J Biomed Imaging 2006:1–7CrossRefGoogle Scholar
  25. 25.
    Khurana AK (2003) Ophthalmology. New Age International Publishers, New DelhiGoogle Scholar
  26. 26.
    Mansour AM (1990) Measuring fundus landmark. Invest Ophthalmol Vis Sci 31:41–42PubMedGoogle Scholar
  27. 27.
    Metz C (2008) ROC analysis in medical imaging: a tutorial review of the literature. Radiol Phys Technol 1:2–12PubMedCrossRefGoogle Scholar
  28. 28.
    Micheli-Tzanakou E (2000) Supervised and unsupervised pattern recognition: feature extraction and computational intelligence. CRC Press, Boca RatonGoogle Scholar
  29. 29.
    Mitchell TM (1997) Machine Learning. McGraw-Hill, New YorkGoogle Scholar
  30. 30.
    Nayak J, Bhat P, Acharya UR et al (2008) Automated identification of diabetic retinopathy stages using digital fundus images. J Med Syst 32:107–115PubMedCrossRefGoogle Scholar
  31. 31.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9:62–66CrossRefGoogle Scholar
  32. 32.
    Parodi MB, Visintin F, Rupe PD, Ravalico G (1995) Foveal avascular zone in macular branch retinal vein occlusion. Int Ophthalmol 19:25–28PubMedCrossRefGoogle Scholar
  33. 33.
    Pratt WK (1978) Digital image processing. Wiley, New YorkGoogle Scholar
  34. 34.
    Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT, Cambridge, MassGoogle Scholar
  35. 35.
    Richard G, Soubrane Gl, Yannuzzi LA, Courland S (1998) Fluorescein and ICG angiography. Thieme Medical, New YorkGoogle Scholar
  36. 36.
    Saini VK, Varma P, Bhaisare V, et al. Foveal Avascular Zone Calculation and its Variation with Different Posterior Segment Diseases and Analysis of its Impact on Best Corrected Visual Acuity. In: Bhattacharyya DD, AIOC 2006. Bhopal, India, 2006; v. 4Google Scholar
  37. 37.
    Sopharak A, Uyyanonvara B, Barman S, Williamson TH (2008) Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Comput Med Imaging Graph 32:720–727PubMedCrossRefGoogle Scholar
  38. 38.
    Stone M (1974) Cross-validatory choice and assessment of statistical predictions. J Royal Stat Soc B 36:111–147Google Scholar
  39. 39.
    Walter T, Klein J-C, Massin P, Erginay A (2002) A contribution of image processing to the diagnosis of diabetic retinopathy-detection of exudates in color fundus images of the human retina. IEEE Trans Med Imaging 21:1236–1243PubMedCrossRefGoogle Scholar
  40. 40.
    Yun WL, Rajendra Acharya U, Venkatesh YV et al (2008) Identification of different stages of diabetic retinopathy using retinal optical images. Inf Sci 178:106–121CrossRefGoogle Scholar
  41. 41.
    Zeffren B, Applegate R, Bradley A, van Heuven W (1990) Retinal fixation point location in the foveal avascular zone. Invest Ophthalmol Vis Sci 31:2099–2105PubMedGoogle Scholar
  42. 42.
    Zweig MH, Campbell G (1993) Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 39:561–577PubMedGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2011

Authors and Affiliations

  • M. H. Ahmad Fadzil
    • 1
  • Lila Iznita Izhar
    • 1
  • Hermawan Nugroho
    • 1
  • Hanung Adi Nugroho
    • 1
  1. 1.Centre for Intelligent Signal and Imaging Research, Department of Electrical and Electronic EngineeringUniversiti Teknologi PETRONASTronohMalaysia

Personalised recommendations