Grading the Severity of Diabetic Macular Edema Cases Based on Color Eye Fundus Images

  • Daniel Welfer
  • Jacob Scharcanski
  • Pablo Gautério Cavalcanti
  • Diane Ruschel Marinho
  • Laura W. B. Ludwig
  • Cleyson M. Kitamura
  • Melissa M. Dal Pizzol
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 6)


Current computer-aided diagnosis (CAD) systems tend to neglect the detection and grading of Diabetic Macular Edema (DME) signs. This chapter introduces a new computer based scheme for detecting and grading DME signs using color eye fundus images. The grading scheme integrates methods for: (a) detecting retinal structures (e.g. optic disk and fovea); (b) detecting lesions in the retina (e.g. exudates); (c) analyzing the spatial distribution of DME signs in the retina; and (d) grading the severity of a DME case as absent, mild, moderate or severe. In a preliminary experimental evaluation of our DME grading scheme using publicly available eye fundus images (i.e., DIARETDB1 image database), an accuracy of 94.29 % was obtained with respect to the mode of the evaluations of the same DME cases by four experts. This is encouraging, since a similar DME grading performance is achieved by a DME expert. In order to calculate the clinicians grading performance, we assumed the mode of all experts DME gradings as the reference evaluation for each case. Thus, if an expert assigned each DME case to the class identified as the mode of the experts severity gradings, that expert achieved an accuracy of 100 %.


Optic Disk Diabetic Macular Edema Grade Scheme Hard Exudate Ground Truth Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Alpaydin E (2004) Introduction to machine learning. Adaptive computation and machine learning. The MIT Press, Cambridge Google Scholar
  2. 2.
    Ciulla TA, Amador AG, Zinman B (2003) Diabetic retinopathy and diabetic macular edema. Diabetes Care 26(9):2653–2664 CrossRefGoogle Scholar
  3. 3.
    Dougherty ER, Lotufo RA (2003) Hands-on morphological image processing. SPIE publications, vol TT59 CrossRefGoogle Scholar
  4. 4.
    Franke J, Halim S (2007) Wild bootstrap tests. IEEE Signal Process Mag 24(4):31–37 CrossRefGoogle Scholar
  5. 5.
    Goh KG, Hsu W, Lee ML, Wang H (2001) ADRIS: an automatic diabetic retinal image screening system. In: Medical data mining and knowledge discovery. Springer, Berlin, pp 181–210 Google Scholar
  6. 6.
    Hayashi JI, Kunieda T, Cole J, Soga R, Hatanaka Y, Lu M, Hara T, Fujita H (2001) A development of computer-aided diagnosis system using fundus images. In: Proceedings of the seventh international conference on virtual systems and multimedia (VSMM’01). IEEE Computer Society, Los Alamitos Google Scholar
  7. 7.
    Jähne B, Haußecker H, Geißler P (1999) Handbook of computer vision and applications: signal processing and pattern recognition, vol 2. Academic Press, New York Google Scholar
  8. 8.
    Kauppi T, Kalesnykiene V, Kämäräinen JK, Lensu L, Sorri I, Raninen A, Voutilainen R, Uusitalo H, Kälviäinen H, Pietilä J (2007) DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Medical image understanding and analysis (MIUA), pp 61–65 Google Scholar
  9. 9.
    Lalonde M, Laliberté F, Gagnon L (2004) RetsoftPlus: a tool for retinal image analysis. In: Proceedings of the 17th IEEE symposium on computer-based medical systems (CBMS’04). IEEE, New York, pp 542–547 CrossRefGoogle Scholar
  10. 10.
    Li H, Chutatape O (2004) Automated feature extraction in color retinal images by a model based approach. IEEE Trans Biomed Eng 51(2):246–254 CrossRefGoogle Scholar
  11. 11.
    Lowell J, Hunter A, Steel D, Basu A, Ryder R, Fletcher E, Kennedy L (2004) Optic nerve head segmentation. IEEE Trans Med Imaging 23(2):256–264 CrossRefGoogle Scholar
  12. 12.
    Meila M, Shi J (2001) A random walks view of spectral segmentation. International conference on AI and statistics (AISTAT) Google Scholar
  13. 13.
    Niemeijer M, Abràmoff MD, Ginneken BV (2007) Segmentation of the optic disc, macula and vascular arch in fundus photographs. IEEE Trans Med Imaging 26:116–127 CrossRefGoogle Scholar
  14. 14.
    Ravishankar S, Jain A, Mittal A (2009) Automated feature extraction for early detection of diabetic retinopathy in fundus images. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Miami Google Scholar
  15. 15.
    Simandjuntak RA, Suksmono AB, Mengko TLR, Sovani I (2005) Development of computer-aided diagnosis system for early diabetic retinopathy based on micro aneurysms detection from retinal images. In: Proceedings of 7th international workshop on enterprise networking and computing in healthcare industry, HEALTHCOM 2005. IEEE, New York, pp 364–367 CrossRefGoogle Scholar
  16. 16.
    Sopharak A, Uyyanonvara B, Barmanb S, Williamson TH (2008) Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Comput Med Imaging Graph 32:720–727 CrossRefGoogle Scholar
  17. 17.
    Tobin KW, Chaum E, Govindasamy VP, Karnowski TP (2007) Detection of anatomic structures in human retinal imagery. IEEE Trans Med Imaging 26(12):1729–1739 CrossRefGoogle Scholar
  18. 18.
    Walter T, Klein JC, 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. Trans Med Imaging 21(10):1236–1243 CrossRefGoogle Scholar
  19. 19.
    Welfer D, Scharcanski J, Kitamura CM, Pizzol MMD, Ludwig LWB, Marinho DR (2010) Segmentation of the optic disk in color eye fundus images using an adaptive morphological approach. Comput Biol Med 40(2):124–137 CrossRefGoogle Scholar
  20. 20.
    Welfer D, Scharcanski J, Marinho DR (2009) A morphological approach for the fovea location in color fundus images. In: International conference on information technology and communications in health. ITCH. Laurel point Inn, Victoria Google Scholar
  21. 21.
    Welfer D, Scharcanski J, Marinho DR (2010) A morphologic three-stage approach for detecting exudates in color eye fundus images. In: 25th symposium on applied computing, ACM SAC’10. ACM, Sierre Google Scholar
  22. 22.
    World Health Organization (2005) Prevention of blindness from diabetes mellitus: report of a WHO consultation in Geneva, Switzerland. Tech rep Google Scholar
  23. 23.
    Yen GG, Leong WF (2008) A sorting system for hierarchical grading of diabetic fundus images: a preliminary study. Trans Inf Technol Biomed 12(1):118–130 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Daniel Welfer
    • 1
  • Jacob Scharcanski
    • 2
  • Pablo Gautério Cavalcanti
    • 2
  • Diane Ruschel Marinho
    • 3
  • Laura W. B. Ludwig
    • 4
  • Cleyson M. Kitamura
    • 4
  • Melissa M. Dal Pizzol
    • 4
  1. 1.UNIPAMPAFederal University of PampaAlegreteBrasil
  2. 2.Institute of InformaticsFederal University of Rio Grande do SulPorto AlegreBrasil
  3. 3.Faculty of MedicineFederal University of Rio Grande do SulPorto AlegreBrasil
  4. 4.Hospital de Clinicas de Porto AlegrePorto AlegreBrasil

Personalised recommendations