Current Diabetes Reports

, Volume 13, Issue 4, pp 453–459 | Cite as

Automated Analysis of Diabetic Retinopathy Images: Principles, Recent Developments, and Emerging Trends

Microvascular Complications-Retinopathy (JK Sun, Section Editor)


Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.


Diabetic retinopathy Computer-aided diagnosis Fundus photography Image analysis Machine learning 



This work was supported in part by the Agency for Healthcare Research and Quality, Grant R21 HS19792-02.

Compliance with Ethics Guidelines

Conflict of Interest

Baoxin Li and Helen K. Li declare that they have no conflict of interest.

Human and Animal Rights and Informed Consent

This article does not contain any studies with human or animal subjects performed by any of the authors.


Papers of particular interest, published recently, have been highlighted as: • Of importance

  1. 1.
    World Health Organization. WHO Fact Sheet No. 312, September 2012. Available at Accessed February 2013.
  2. 2.
    Kinyoun JL, Martin DC, Fujimoto WY, et al. Ophthalmoscopy versus fundus photographs for detecting and grading diabetic retinopathy. Invest Ophthalmol Vis Sci. 1992;33(6):1888–93.PubMedGoogle Scholar
  3. 3.
    Pugh JA, Jacobson JM, Van Heuven WA, et al. Screening for diabetic retinopathy: the wide-angle retinal camera. Diabetes Care. 1993;16(6):889–95.PubMedCrossRefGoogle Scholar
  4. 4.
    Bursell SE, Cavallerano JD, Cavallerano AA, et al. Stereo nonmydriatic digital-video color retinal imaging compared with Early Treatment Diabetic Retinopathy Study seven standard field 35-mm stereo color photos for determining level of diabetic retinopathy. Ophthalmology. 2001;108(3):572–85.PubMedCrossRefGoogle Scholar
  5. 5.
    Lin DY, Blumenkranz MS, Brothers RJ, et al. The sensitivity and specificity of single-field nonmydriatic monochromatic digital fundus photography with remote image interpretation for diabetic retinopathy screening: a comparison with ophthalmoscopy and standardized mydriatic color photography. Am J Ophthalmol. 2002;134(2):204–13.PubMedCrossRefGoogle Scholar
  6. 6.
    Matsui M, Tashiro T, Matsumoto K, et al. A study on automatic and quantitative diagnosis of fundus photographs. I. Detection of contour line of retinal blood vessel images on color fundus photographs. Nihon Ganka Gakkai Zasshi. 1973;77(8):907–18.PubMedGoogle Scholar
  7. 7.
    Baudoin CE, Lay BJ, Klein JC. Automatic detection of microaneurysms in diabetic fluorescein angiographies. Rev D’Épidémiol Sante Publique. 1984;32:254–61.Google Scholar
  8. 8.
    Teng T, Lefley M, Claremont D. Progress towards automated diabetic ocular screening: a review of image analysis and intelligent systems for diabetic retinopathy. Med Biol Eng Comput. 2002;40(1):2–13.PubMedCrossRefGoogle Scholar
  9. 9.
    Patton N, Aslam TM, MacGillivray T, et al. Retinal image analysis: concepts, applications and potential. Prog Retin Eye Res. 2006;25(1):99–127.PubMedCrossRefGoogle Scholar
  10. 10.
    • Abràmoff MD, Garvin MK, Sonka M. Retinal imaging and image analysis. IEEE Rev Biomed Eng. 2010;3:169–208. This presents a review of retinal imaging and image analysis methods and their clinical implications, covering studies before September 2010.PubMedCrossRefGoogle Scholar
  11. 11.
    Faust O, Acharya UR, Ng EY, et al. Algorithms for the automated detection of diabetic retinopathy using digital fundus images: a review. J Med Syst. 2012;36(1):145–57.PubMedCrossRefGoogle Scholar
  12. 12.
    Wang Y, Tan W, Lee SC. Illumination normalization of retinal images using sampling and interpolation. In: Proc. of SPIE Medical Imaging 2001, San Diego, CA.Google Scholar
  13. 13.
    Osareh A, Mirmehd M, Thomas B, Markham R. Comparison of colour spaces for optic disc localisation in retinal images. In: Proc. 16th Intl. Conf. on Pattern Recognition. Quebec City, Quebec, Canada, 2002, 743–746.Google Scholar
  14. 14.
    Abdel-Razik A, Ghalwash AZ, Abdel-Rahman A. Optic disc detection from normalized digital fundus images by means of a vessels’ direction matched filter. IEEE Trans Med Imag. 2008;27(1):11–8.Google Scholar
  15. 15.
    Lee S, Abràmoff MD, Reinhardt JM, et al. Validation of retinal image registration algorithms by a projective imaging distortion model. In: Proc. of the 29th Intl. Conf. of the IEEE EMBS, Lyon, France, Aug. 2007.Google Scholar
  16. 16.
    Peli B, Augliere RA, Timberlake GT. Feature-based registration for retinal images. IEEE Trans Med Imaging. 1987;6(3):272–8.PubMedCrossRefGoogle Scholar
  17. 17.
    Cideciyan AV. Registration of ocular fundus images: an algorithm using cross-correlation of triple invariant image descriptors. IEEE Eng Med Biol Mag. 1995;14(1):52–8.CrossRefGoogle Scholar
  18. 18.
    Pinz A, Bernogger S, Datlinger P, et al. Mapping the human retina. IEEE Trans Med Imag. 1998;17(4):606–19.CrossRefGoogle Scholar
  19. 19.
    Deng K, Tian J, Zheng J, et al. Retinal fundus image registration via vascular structure graph matching. Int J Biomed Imaging, vol. 2010, Article ID 906067, 13 pages. doi: 10.1155/2010/906067
  20. 20.
    Goldbaum M, Moezzi S, Taylor A, et al. Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images. In: Proc. IEEE Intl. Conf. Image Processing, 1996, Lausanne, Switzerland.Google Scholar
  21. 21.
    Sinthanayothin C, Boyce JF, Cook HL, Williamson TH. Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br J Ophthalmol. 1999;83(8):902–10.PubMedCrossRefGoogle Scholar
  22. 22.
    Hoover A, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imag. 2000;19(3):203–10.CrossRefGoogle Scholar
  23. 23.
    Gagnon L, Lalonde M, Beaulieu M, et al. Procedure to detect anatomical structures in optical fundus images. In: Proc. of SPIE Medical Imaging 2001, San Diego, CA.Google Scholar
  24. 24.
    Hoover A, Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels. IEEE Trans Med Imag. 2003;22(8):951–8.CrossRefGoogle Scholar
  25. 25.
    Staal J, Abràmoff MD, Niemeijer M, et al. Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imag. 2004;23(4):501–9.CrossRefGoogle Scholar
  26. 26.
    Tobin KW, Chaum E, Govin VP. Detection of anatomic structures in human retinal imagery. IEEE Trans Med Imag. 2007;26(12):1729–40.CrossRefGoogle Scholar
  27. 27.
    Youssif AR, Ghalwash AZ, Ghoneim AR. Optic disc detection from normalized digital fundus images by means of a vessels' direction matched filter. IEEE Trans Med Imag. 2008;27(1):11–8.CrossRefGoogle Scholar
  28. 28.
    Al-Diri B, Hunter A, Steel D. An active contour model for segmenting and measuring retinal vessels. IEEE Trans Med Imag. 2009;28(9):1488–97.CrossRefGoogle Scholar
  29. 29.
    Aquino A, Gegúndez-Arias ME, Marín D. Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques. IEEE Trans Med Imag. 2010;29(11):1860–9.CrossRefGoogle Scholar
  30. 30.
    Mahfouz AE, Fahmy AS. Fast localization of the optic disc using projection of image features. IEEE Trans Imag Proc. 2010;19(12):3285–9.CrossRefGoogle Scholar
  31. 31.
    Lupascu CA, Tegolo D, Trucco E. FABC: retinal vessel segmentation using AdaBoost. IEEE Trans Info Tech Biomed. 2010;14(5):1267–74.CrossRefGoogle Scholar
  32. 32.
    Hipwell JH, Strachant F, Olson JA, et al. Automated detection of microaneurysms in digital red-free photographs: a diabetic retinopathy screening tool. Diabet Med. 2000;17:588–94.PubMedCrossRefGoogle Scholar
  33. 33.
    Mizutani A, Muramatsu C, Hatanaka Y, et al. Automated microaneurysm detection method based on double-ring filter in retinal fundus images. In: Proc. of SPIE Medical Imaging 2009: Computer-Aided Diagnosis, edited by Nico Karssemeijer, Maryellen L. Giger, Proc. of SPIE Vol. 7260, 1605–7422, doi: 10.1117/12.813468.
  34. 34.
    Quellec G, Lamard M, Josselin P, et al. Optimal wavelet transform for the detection of microaneurysms in retina photographs. IEEE Trans Med Imag. 2008;27(9):1230–41.CrossRefGoogle Scholar
  35. 35.
    Quellec G, Russell SR, Abràmoff MD. Optimal filter framework for automated, instantaneous detection of lesions in retinal images. IEEE Trans Med Imag. 2011;30(2):523–33.CrossRefGoogle Scholar
  36. 36.
    Osareh A, Mirmehdi M, Thomas B, et al. Automated identification of diabetic retinal exudates in digital colour images. Br J Ophthalmol. 2003;87:1220–3.PubMedCrossRefGoogle Scholar
  37. 37.
    Jaafar HF, Nandi AK, Al-Nuaimy W. Detection of exudates in retinal images using a pure splitting technique. In: Prod. 32th Intl. Conf. of IEEE EMBS, Buenos Aires, Argentina, August 31–September 4, 2010.Google Scholar
  38. 38.
    Agurto C, Murray V, Barriga E, et al. Multiscale AM-FM methods for diabetic retinopathy lesion detection. IEEE Trans Med Imag. 2010;29(2):502–12.CrossRefGoogle Scholar
  39. 39.
    Hassan S, Bong D, Premsenthi M. Detection of neovascularization in diabetic retinopathy”. J Digit Imaging. 2012;25:437–44.PubMedCrossRefGoogle Scholar
  40. 40.
    Agurto C, Yu H, Murray V, et al. Detection of neovascularization in the optic disc using an AM-FM representation, granulometry, and vessel segmentation. In: 34th Intl. Conf. of IEEE EMBS, San Diego, CA, August, 2012.Google Scholar
  41. 41.
    Osareh A, Mirmehdi M, Thomas B et al. Classification and localisation of diabetic-related eye disease. In: Proceedings of the European Conference on Computer Vision 2002:502–516. Springer-Verlag.Google Scholar
  42. 42.
    Walter T, Massin P, Erginay A, et al. Automatic detection of microaneurysms in color fundus images. Med Image Anal. 2007;11(6):555–66. Epub 2007 May 26.PubMedCrossRefGoogle Scholar
  43. 43.
    Jaafar HF, Nandi AK, Al-Nuaimy W. Decision support system for the detection and grading of hard exudates from color fundus photographs. J Biomed Optics. 2011;16(11):116001-1-11.CrossRefGoogle Scholar
  44. 44.
    Giancardo L, Meriaudeau F, Karnowski TP, et al. Exudate-based diabetic macular edema detection in fundus images using publicly available datasets. Med Image Anal. 2012;16:216–26.PubMedCrossRefGoogle Scholar
  45. 45.
    Cheng X, Wong D, Liu J, Lee B, et al. Automatic localization of retinal landmarks. In: 34th Intl. Conf. of IEEE EMBS, San Diego, California USA, August, 2012.Google Scholar
  46. 46.
    Lazebnik S, Schmid C, Ponce J. A sparse texture representation using local affine regions. IEEE Trans PAMI. 2005;27(8):1265–78.CrossRefGoogle Scholar
  47. 47.
    Sivic J, Zisserman A. Video google: a text retrieval approach to object matching in videos. In: Proc IEEE Intl Conf Computer Vision. 2003; pp. 1470–1477.Google Scholar
  48. 48.
    Ma J, Plonka G. The curvelet transform: a review of recent applications. IEEE Signal Process Mag. 2010;27(2):118–33.CrossRefGoogle Scholar
  49. 49.
    Li C, Xu C, Gui C, Fox MD. Level set evolution without re-initialization: a new variational formulation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition 2005, vol. 1, pp. 430–436.Google Scholar
  50. 50.
    Esmaeili M, Rabbani H, Dehnavi AM, Dehghani A. Automatic detection of exudates and optic disk in retinal images using curvelet transform. IET Image Process. 2012;6(7):1005–13.CrossRefGoogle Scholar
  51. 51.
    Sun K, Chen Z, Jiang S. Local morphology fitting active contour for automatic vascular segmentation. IEEE Trans Biomed Eng. 2012;59(2):464–73.PubMedCrossRefGoogle Scholar
  52. 52.
    Li C, Kao C, Gore JC, Ding Z. Implicit active contours driven by local binary fitting energy. In: Proc IEEE Conf Comput Vis Pattern Recognit 2007, vol. 1, pp. 1–7.Google Scholar
  53. 53.
    Antal B, Lazar I, Hajdu A. An adaptive weighting approach for ensemble-based detection of microaneurysms in color fundus images. In: 34th Intl. Conf. of IEEE EMBS, San Diego, California USA, August, 2012.Google Scholar
  54. 54.
    Antal B, Hajdu A. An ensemble-based system for microaneurysm detection and diabetic retinopathy grading. IEEE Trans Biomed Eng. 2012;59(6):1720–6.PubMedCrossRefGoogle Scholar
  55. 55.
    Jelinek HF, Pires R, Padilha R, et al. Data fusion for multi-lesion diabetic retinopathy detection. In: Proc 25th IEEE Intl Symp Computer-Based Medical Systems, Rome, Italy, 20–22 June 2012.Google Scholar
  56. 56.
    Fleming AD, Goatman KA, Philip S, et al. The role of haemorrhage and exudate detection in automated grading of diabetic retinopathy. Br J Ophthalmol. 2010;94:706–11.PubMedCrossRefGoogle Scholar
  57. 57.
    Massey EM, Hunter A. Augmenting the classification of retinal lesions using spatial distribution. In: Proc of 33rd Intl Conf of IEEE EMBS, Boston, MA, August 30–September 3, 2011.Google Scholar
  58. 58.
    Quellec G, Lamard M, Abràmoff MD, et al. A multiple-instance learning framework for diabetic retinopathy screening. Med Image Anal. 2012;16:1228–40.PubMedCrossRefGoogle Scholar
  59. 59.
    Goatman KA, Fleming AD, Philip S, et al. Detection of new vessels on the optic disc using retinal photographs. IEEE Trans Med Imag. 2011;30(4):972–9.CrossRefGoogle Scholar
  60. 60.
    Marín D, Aquino A, Emilio M, et al. A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE Trans Med Imag. 2011;30(1):146–58.CrossRefGoogle Scholar
  61. 61.
    Lazar I, Hajdu A. Segmentation of vessels in retinal images based on directional height statistics. In: Proc 34th Intl Conf of IEEE EMBS, San Diego, California USA, 28 August–1 September, 2012.Google Scholar
  62. 62.
    Lu S, Lim JH. Automatic optic disc detection from retinal images by a line operator. IEEE Trans Biomed Eng. 2011;58(1):88–94.PubMedCrossRefGoogle Scholar
  63. 63.
    Yu H, Barriga ES, Agurto C. Fast localization and segmentation of optic disk in retinal images using directional matched filtering and level sets. IEEE Trans Info Tech Biomed. 2012;16(4):644–57.CrossRefGoogle Scholar
  64. 64.
    Hatanaka Y, Inoue T, Okumura S, et al. Automated microaneurysm detection method based on double-ring filter and feature analysis in retinal fundus images. In: Proc 25th IEEE Intl Symp Computer-Based Medical Systems, Rome, Italy, 20–22 June 2012.Google Scholar
  65. 65.
    Akram MU, Tariq A, Anjum MA, et al. Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy. Appl Optics. 2012;51(20):4858–66.CrossRefGoogle Scholar
  66. 66.
    • Niemeijer M, van Ginneken B, Cree M, et al. Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imaging. 2010;29(1):185–95. This reports results from the first international microaneurysm detection competition. The comparative study on five different methods based on a common data set revealed the less-than-desired accuracy of the existing methods.PubMedCrossRefGoogle Scholar
  67. 67.
    Abramoff MD, Niemeijer M, Suttorp-Schulten M, et al. Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes. Diabetes Care. 2008;31:193–8.PubMedCrossRefGoogle Scholar
  68. 68.
    Olson JA, Sharp PF, Fleming A, et al. Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes: response to Abrámoff et al. Diabetes Care. 2008;31(8):e63.PubMedCrossRefGoogle Scholar
  69. 69.
    Itti L, Koch C. Computational modeling of visual attention. Nat Rev Neurosci. 2001;2(3):194–203.PubMedCrossRefGoogle Scholar
  70. 70.
    Tiersma E, Peters A, Mooij H, et al. Visualising scanning patterns of pathologists in the grading of cervical intraepithelial neoplasia. J Clin Pathol. 2003;56(9):677–80.PubMedCrossRefGoogle Scholar
  71. 71.
    Manning D, Ethell S, Donovan T, Crawford T. How do radiologists do it? The influence of experience and training on searching for chest nodules. Radiography. 2006;12(2):134–42.CrossRefGoogle Scholar
  72. 72.
    Mello-Thoms C, Ganott M, Sumkin J, Hakim C, et al. Different search patterns and similar decision outcomes: how can experts agree in the decisions they make when reading digital mammograms? Digital Mammography 2008, 212–219.Google Scholar
  73. 73.
    Cavallerano JD, Patel B, Silva PS, et al. Imager evaluation of diabetic retinopathy at the time of imaging in a telemedicine program. Diabetes Care. 2012;35(3):482–4.PubMedCrossRefGoogle Scholar
  74. 74.
    Gupta A, Moexxi S, Taylor A, Chatterjee S, et al. Content-based retrieval of ophthalmological images. In: Proc IEEE Intl Conf Imag Processing, 1996, Lausanne, Switzerland.Google Scholar
  75. 75.
    i-Andaloussi S, Lamard M, Cazuguel G, et al. Content based medical image retrieval based on BEMD: optimization of a similarity metric. In: Proc 32nd Intl Conf of IEEE EMBS, Buenos Aires, Argentina, August 31–September 4, 2010.Google Scholar
  76. 76.
    Quellec G, Lamard M, Cazuguel G, et al. Automated assessment of diabetic retinopathy severity using content-based image retrieval in multimodal fundus photographs. Investig Ophthalmol Vis Sci. 2011;52(11):8342–9.CrossRefGoogle Scholar
  77. 77.
    • Chandakkar PS, Venkatesan R, Li B. Retrieving clinically relevant diabetic retinopathy images using a multi-class multiple-instance framework. In: Proc. SPIE Medical Imaging, Orlando, FL, February 2013. This present a new perspective of supporting DR diagnosis by retrieving images with similar levels of DR severity through a recent machine-learning technique that does not require localized labeling. Google Scholar
  78. 78.
    Sanchez CI, Niemeijer M, Abramoff MD, et al. Active learning for an efficient training strategy of computer-aided diagnosis systems: application to diabetic retinopathy screening. In: Proc. the 13th Intl. Conf. on Medical Image Computing and Computer Assisted Intervention. Beijing, China, September 2010.Google Scholar
  79. 79.
    Xu X, Li B. Automatic classification and detection of clinically-relevant images for diabetic retinopathy. In Proc. SPIE Medical Imaging, San Diego, CA, USA, Feb. 2008.Google Scholar
  80. 80.
    Venkatesan R, Chandakkar P, Li B, et al. Classification of diabetic retinopathy images using multi-class multiple-instance learning based on color correlogram features. In: 34th Intl. Conf. of IEEE EMBS, San Diego, CA, August, 2012.Google Scholar
  81. 81.
    Branson S, Wah C, Babenko B, et al. Visual recognition with humans in the loop. In: Proc. European Conference on Computer Vision, Heraklion, Crete, Sept. 2010.Google Scholar
  82. 82.
    Nowak S, Ruger S. How reliable are annotations via crowdsourcing: a study about inter-annotator agreement for multi-label image annotation. In: Proc. the Intl. Conf. on Multimedia Info. Retrieval. 2010 pp. 557–566.Google Scholar
  83. 83.
    Goldman D, Brandt J. Task decomposition and human computation in graphics and vision. In: ACM CHI 2011 Workshop on Crowdsourcing and Human computation, 2011.Google Scholar
  84. 84.
    Xu X, Li B, Florez JF, et al. Simulation of diabetic retinopathy neovascularization in color digital fundus images. In Advances in Visual Computing, G. Bebis et al. (Eds.), pp. 421–433, Springer-Verlag, 2006. Springer Lecture Notes in Computer Science (LNCS) 4291 for International Symposium on Visual Computing 2006.Google Scholar
  85. 85.
    Hu Z, Niemeijer M, Abràmoff MD, et al. Multimodal retinal vessel segmentation from spectral-domain optical coherence tomography and fundus photography. IEEE Trans Med Imag. 2012;31(10):1900–11.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.School of Computing, Informatics & Decision Systems EngineeringArizona State UniversityTempeUSA
  2. 2.Weill Cornell Medical College / The Methodist HospitalHoustonUSA
  3. 3.School of Biomedical InformaticsThe University of Texas Health Science CenterHoustonUSA
  4. 4.Department of OphthalmologyThomas Jefferson UniversityPhiladelphiaUSA

Personalised recommendations