Medical Engineering & Physics
Volume 32, Issue 10 , Pages 1085-1093 , December 2010

Assessment of four neural network based classifiers to automatically detect red lesions in retinal images

  • María García

      Affiliations

    • Grupo de Ingeniería Biomédica, E.T.S. Ingenieros de Telecomunicación, University of Valladolid, Paseo Belén 15, 47011 Valladolid, Spain
    • Corresponding Author InformationCorresponding author. Tel.: +34 983423983; fax: +34 983423667.
    • ,
  • María I. López

      Affiliations

    • Instituto de Oftalmobiología Aplicada (IOBA), University of Valladolid, Valladolid, Spain
    • ,
  • Daniel Álvarez

      Affiliations

    • Grupo de Ingeniería Biomédica, E.T.S. Ingenieros de Telecomunicación, University of Valladolid, Paseo Belén 15, 47011 Valladolid, Spain
    • ,
  • Roberto Hornero

      Affiliations

    • Grupo de Ingeniería Biomédica, E.T.S. Ingenieros de Telecomunicación, University of Valladolid, Paseo Belén 15, 47011 Valladolid, Spain

Received 30 October 2009 ,Revised 20 May 2010 ,Accepted 26 July 2010.

References 

  1. World Health Organisation . Prevention of blindness from diabetes mellitus: report of a WHO consultation in Geneva, Switzerland. Switzerland: WHO Library Cataloguing-in-Publication Data; 2005;
  2. Ong GL, Ripley LG, Newsom RS, Cooper M, Casswell AG. Screening for sight-threatening diabetic retinopathy: comparison of fundus photography with automated color contrast threshold test. Am J Ophthalmol. 2004;17:445–452
  3. Fong DS, Aiello L, Gardner TW, King GL, Blankenship G, Cavallerano JD, et al. Diabetic retinopathy. Diabetes Care. 2003;26:226–229
  4. Diabetic Retinopathy Clinical Research Network . The course of response to focal/grid photocoagulation for diabetic macular edema. Retina. 2009;29:1436–1443
  5. Diabetic Retinopathy Clinical Research Network . A randomized trial comparing intravitreal triamcinolone acetonide and focal/grid photocoagulation for diabetic macular edema. Ophthalmology. 2008;115:1447–59, 1459.e1–10
  6. Taylor CR, Lawrence MM, Salunga AM, Hepworth JT, Crutcher TD, O’Day DM, et al. Improving diabetic retinopathy screening ratios using telemedicine-based digital retinal imaging technology. Diabetes Care. 2007;30:574–578
  7. Niemeijer M, van Ginneken B, Staal J, Suttorp-Schulten MSA, Abràmoff M. Automatic detection of red lesions in digital color fundus photographs. IEEE Trans Med Imaging. 2005;24:584–592
  8. Lin DY, Blumenkranz MS, Brothers SJ, Grosvenor DM. 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;134:204–213
  9. Niemeijer M, van Ginneken B, Russell SR, Suttorp-Schulten MSA, Abràmoff M. Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. Invest Ophthalmol Vis Sci. 2007;48:2260–2267
  10. García M, Sánchez CI, López MI, Abásolo D, Hornero R. Neural network based detection of hard exudates in retinal images. Comput Methods Programs Biomed. 2009;93:9–19
  11. García M, Sánchez CI, Poza J, López MI, Hornero R. Detection of hard exudates in retinal images using a radial basis function classifier. Ann Biomed Eng. 2009;37:1448–1463
  12. Sinthanayothin C, Boyce JF, Williamson TH, Cook HL, Mensah E, Lal S, et al. Automated detection of diabetic retinopathy on digital fundus images. Diabetic Med. 2002;19:105–112
  13. Ege BM, Hejlesen OK, Larsen OV, Møller K, Jennings B, Kerr D, et al. Screening for diabetic retinopathy using computer based image analysis and statistical classification. Comput Methods Programs Biomed. 2000;62:165–175
  14. Spencer T, Olson JA, McHardy KC, Sharp PF, Forrester JV. An image-processing strategy for the segmentation and quantification of microaneurysms in fluorescein angiograms of the ocular fundus. Comput Biomed Res. 1996;29:284–302
  15. Frame AJ, Undrill PE, Cree MJ, Olson JA, McHardy KC, Sharp PF, et al. A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic fluorescein angiograms. Comput Biol Med. 1998;28:225–238
  16. Grisan E, Ruggeri A. Segmentation of candidate dark lesions in fundus images based on local thresholding and pixel density. In: Proceedings of the 29th annual international conference of IEEE engineering in medicine and biology society. 2007;
  17. Gardner GG, Keating D, Williamson TH, Elliot AT. Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. Br J Ophthalmol. 1996;80:940–944
  18. Zhang X, Chutatape O. Top-down and bottom-up strategies in lesion detection of background diabetic retinopathy. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition. 2005;
  19. Grisan E, Ruggeri A. A hierarchical Bayesian classification for non-vascular lesions detection in fundus images. In: Proceedings of the 3rd European medical and biological engineering conference. 2005;
  20. Walter T, Massin P, Erginay A, Ordonez R, Jeulin C, Klein J-C. Automatic detection of microaneurysms in color fundus images. Med Image Anal. 2007;11:555–566
  21. Quellec G, Lamard M, Josselin PM, Cazugel G, Cochener B, Roux C. Optimal wavelet transform for the detection of microaneurysms in retina photographs. IEEE Trans Med Imaging. 2008;27:1230–1241
  22. Osareh A, Shadgar B, Markham R. A computational-intelligence-based approach for detection of exudates in diabetic retinopathy images. IEEE Trans Inf Technol Biomed. 2009;13:535–545
  23. 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;40:2–13
  24. Foracchia M, Grisan E, Ruggeri A. Luminosity and contrast normalization in retinal images. Med Image Anal. 2005;9:179–190
  25. Sánchez CI. Retinal image analysis by mixture model based clustering and discriminant analysis for automatic detection of hard exudates and haemorrhages. A tool for diabetic retinopathy screening. Ph.D. thesis. Valladolid; 2008.
  26. Hoover A, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging. 2000;19:203–210
  27. Soille P. Morphological image analysis: principles and applications. New York: Springer-Verlag; 1999;
  28. Mendoça AM, Campilho A. Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans Med Imaging. 2006;25:1200–1213
  29. Osareh A. Automated identification of diabetic retinal exudates and the optic disc. Ph.D. thesis. Bristol; 2004.
  30. Sleigh JW, Steyn-Ross DA, Steyn-Ross ML, Grant C, Ludbrook G. Cortical entropy changes with general anaesthesia: theory and experiment. Physiol Meas. 2004;25:921–934
  31. Sonka M, Hlavac V, Boyle R. Image processing, analysis and machine vision. London: International Thomson Computer Press; 1996;
  32. Loew MH. Feature extraction. In:  Sonka M,  Fitzpatrick JM editor. Handbook of medical imaging. Bellingham: SPIE Press; 2000;p. 273–341
  33. Nadler M, Smith E. Pattern recognition engineering. New York: John Wiley; 1993;
  34. Hosmer DW, Lemeshow S. Applied logistic regression. New York: John Wiley & Sons; 1989;
  35. Jobson JD. Applied multivariate data analysis: categorical and multivariate methods. New York: Springer; 1991;
  36. Haykin S. Neural networks: a comprehensive foundation. Upper Saddle River, NJ: Prentice-Hall International; 1999;
  37. Bishop CM. Neural networks for pattern recognition. New York: Oxford University Press Inc.; 1995;
  38. Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Netw. 1991;4:251–257
  39. Huang G-B, Chen Y-Q, Babri HA. Classification ability of single hidden layer feedforward neural networks. IEEE Trans Neural Netw. 2000;11:799–801
  40. Chen S, Cowan CFN, Grant PM. Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Netw. 1991;2:302–309
  41. Intelligent Data Analysis Group . SVM toolbox for Matlab. 2002;http://ida.first.fraunhofer.de/∼anton/software.html
  42. Moody J . Prediction risk and architecture selection for neural networks. In:  Cherkassky V,  Friedman JH,  Wechsler H editor. From statistics to neural networks: theory and pattern recognition applications. Springer-Verlag; 1994;
  43. Javitt JC, Canner JK, Frank RG, Steinwachs DM, Sommer A. Detecting and treating retinopathy in patients with type I diabetes mellitus. A health policy model. Ophthalmology. 1990;97:483–494
  44. Working Party of the British Diabetic Association . Retinal photography screening for diabetic eye disease. A British Diabetic Association Report, London. 1997;
  45. Niemeijer M, van Ginneken B, Cree MJ, Mizutani A, Quellec G, Sánchez CI, et al. Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imaging. 2010;29:185–195

PII: S1350-4533(10)00166-9

doi: 10.1016/j.medengphy.2010.07.014

Medical Engineering & Physics
Volume 32, Issue 10 , Pages 1085-1093 , December 2010

Article Tools

* Image Usage & Resolution