Unsupervised Change Detection in Multitemporal Images of the Human Retina

  • Giulia TroglioEmail author
  • Jon Atli Benediktsson
  • Gabriele Moser
  • Sebastiano Bruno Serpico
  • Einar Stefansson


Diabetes is a growing epidemic in the world, due to population growth, aging, urbanization, and increasing prevalence of obesity and physical inactivity. Diabetic retinopathy is the leading cause of blindness in the western working age population. Early detection can enable timely treatment minimizing further deterioration. Clinical signs observable by digital fundus imagery, include microaneurysms, hemorrhages, and exudates, among others. In this chapter, a new method to help the diagnosis of retinopathy and to be used in automated systems for diabetic retinopathy screening is presented. In particular, the automatic detection of temporal changes in retinal images is addressed. The images are acquired from the same patient during different medical visits by a color fundus camera. The presented method is based on the preliminary automatic registration of multitemporal images, and the detection of the temporal changes in the retina, by comparing the registered images. An automatic registration approach, based on the extraction of the vascular structures in the images to be registered and the optimization of their match, is proposed. Then, in order to achieve the detection of temporal changes, an unsupervised approach, based on a minimum-error thresholding technique, is proposed. The algorithm is tested on color fundus images with small and large changes.


Retinal imaging Change-detection Image registration Segmentation 



This work was partially supported by the Research of Fund of the University of Iceland.


  1. 1.
    Berger JW, Shin DS (1999) Computer vision enabled augmented reality fundus biomicroscopy. Ophthalmology 106:1935–1941PubMedCrossRefGoogle Scholar
  2. 2.
    Cree MJ, Olson JA, McHardy KC, Sharp PF, Forrester JV (1997) A fully automated comparative microaneurysm digital detection system. Eye 11:622–628PubMedGoogle Scholar
  3. 3.
    Usher D, Dumskyj M, Himaga M, Williamson TH, Nussey S, Boyce J (2003) Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening. Diabet Med 21:84–90CrossRefGoogle Scholar
  4. 4.
    Walter T, Klein JC, Massin P, Erginary 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(10):1236–1243PubMedCrossRefGoogle Scholar
  5. 5.
    Laliberté F, Gagnon L, Sheng Y (2003) Registration and fusion of retinal images – an evaluation study. IEEE Trans Med Imaging 22:661–673PubMedCrossRefGoogle Scholar
  6. 6.
    Kittler J, Illingworth J (1986) Minimum error thresholding. Pattern Recognit 19(1):41–47CrossRefGoogle Scholar
  7. 7.
    Algazi VR, Keltner JL, Johnson CA (1985) Computer analysis of the optic cup in glaucoma. Invest Ophthalmol Vis Sci 26:1759–1770PubMedGoogle Scholar
  8. 8.
    Peli E, Lahav M (1986) Drusement measurement from Fundus photographs using computer image analysis. Opthalmology 93:1575–1580Google Scholar
  9. 9.
    Phillips RP, Spencer T, Ross PG, Sharp PF, Forrester JV (1991) Quantification of diabetic maculopathy by digital imaging of the fundus. Eye 5:130–137PubMedGoogle Scholar
  10. 10.
    Brown L (1992) A survey of images registration techniques. ACM Comput Surv 24(4):326–376CrossRefGoogle Scholar
  11. 11.
    Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21:977–1000CrossRefGoogle Scholar
  12. 12.
    Cideciyan AV (1995) Registration of ocular fundus images. IEEE Eng Med Biol Mag 14:52–58CrossRefGoogle Scholar
  13. 13.
    Can A, Shen H, Turner JN, Tanenbaum HL, Roysam B (1999) Rapid automated tracing and feature extraction from live high-resolution retinal fundus images using direct exploratory algorithms. IEEE Trans Inform Technol Biomed 3(2):125–138CrossRefGoogle Scholar
  14. 14.
    Hoover A, Kouznetsova V, Goldbaum N (2000) Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging 19(3):203–210PubMedCrossRefGoogle Scholar
  15. 15.
    Staal J, Abramoff M, Niemeijer M, Viergever M, van Ginneken B (2004) Ridge based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4):501–509PubMedCrossRefGoogle Scholar
  16. 16.
    Hoover A, Goldbaum M (2003) Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels. IEEE Trans Med Imaging 22(8):951–958PubMedCrossRefGoogle Scholar
  17. 17.
    Lowell J, Hunter A, Steel D, Basu A, Ryder R, Fletcher E (2004) Optic nerve head segmentation. IEEE Trans Med Imaging 23(2):256–264PubMedCrossRefGoogle Scholar
  18. 18.
    Foracchia M, Grisan E, Ruggeri A (2004) Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE Trans Med Imaging 23(10):1189–1195PubMedCrossRefGoogle Scholar
  19. 19.
    Pinz A, Bernogger S, Datlinger P, Kruger A (1998) Mapping the human retina. IEEE Trans Med Imaging 17(4):606–620PubMedCrossRefGoogle Scholar
  20. 20.
    Peli E, Augliere RA, Timberlake GT (1987) Feature-based registration of retinal images. IEEE Trans Med Imaging 6(3):272–278PubMedCrossRefGoogle Scholar
  21. 21.
    Goldbaum MH, Kouznyetsova V, Cote B, Nelson M, Hart WE (1993) Automated registration of digital ocular fundus images for comparison of lesions. In: Proceedings of ophthalmic technologies III, SPIE, vol 1877, no 1, pp 94–99Google Scholar
  22. 22.
    Zana F, Klein J (1999) A multimodal registration algorithm of eye fundus images using vessels detection and Hough transform. IEEE Trans Med Imaging 18(5):419–428PubMedCrossRefGoogle Scholar
  23. 23.
    Domingo J, Ayala G, Simo A, de Ves E (1997) Irregular motion recovery in fluorescin angiograms. Pattern Recognit Lett 18:805–821CrossRefGoogle Scholar
  24. 24.
    Can CV, Stewart BR, Tanenbaum HL (2002) A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina. IEEE Trans Inform Technol Biomed 3(2):125–138CrossRefGoogle Scholar
  25. 25.
    Stewart V, Tsai C-L, Roysam B (2003) The dual-bootstrap iterative closest point algorithm with application to retinal image registration. IEEE Trans Med Imaging 22(11):1379–1394PubMedCrossRefGoogle Scholar
  26. 26.
    Kuglin CD, Hines DC (1975) The phase correlation image alignment method. In: Proceeding of the international conference on cybernetics and society, pp 163–165Google Scholar
  27. 27.
    De Castro E, Cristini G, Martelli A, Morandi C, Vascotto M (1987) Compensation of random eye motion in television ophthalmoscopy: preliminary results. IEEE Trans Med Imaging 6:74–81PubMedCrossRefGoogle Scholar
  28. 28.
    De Castro E, Morandi C (1987) Registration of translated and rotated images using finite fourier transforms. IEEE Trans Pattern Anal Mach Intell 9:700–703CrossRefGoogle Scholar
  29. 29.
    Ritter N, Owens R, Cooper J, Eikelboom RH, Saarloos PPV (1999) Registration of stereo and temporal images of the retina. IEEE Trans Med Imaging 18(5):404–418PubMedCrossRefGoogle Scholar
  30. 30.
    Butz T, Thiran J-P (2001) Affine registration with feature space mutual information. In: Niessen WJ, Viergever MA (eds) Medical image computing and computer-assisted intervention, vol 2208 of Lecture notes in computer science, Springer, Berlin, Germany, pp 549–556Google Scholar
  31. 31.
    Matsopoulos GK, Mouravliansky NA, Delibasis KK, Nikita KS (1999) Automatic retinal image registration scheme using global optimisation techniques. IEEE Trans Inform Technol Biomed 3(1):47–60CrossRefGoogle Scholar
  32. 32.
    Deer P, Eklund P (2002) Values for the fuzzy C-means classifier in change detection for remote sensing. In: Proceedings of the 9th international conference on information processing and management of uncertainty, IPMU 2002, pp 187–194Google Scholar
  33. 33.
    Oliver C, Quegan S (1998) Understanding synthetic aperture radar images. Artech House, Norwood, MAGoogle Scholar
  34. 34.
    Rignot EJM, Van Zyl JJ (1993) Change detection techniques for ERS-1 SAR data. IEEE Trans Geosci Remote Sens 31(4):896–906CrossRefGoogle Scholar
  35. 35.
    White RG (1990) Change detection in SAR imagery. Int J Remote Sens 12(2):339–360CrossRefGoogle Scholar
  36. 36.
    Li X, Yeh AG (2004) Multitemporal SAR images for monitoring cultivation systems using case-based reasoning. Remote Sens Environ 90(4):524–534CrossRefGoogle Scholar
  37. 37.
    Bruzzone L, Prieto DF, Serpico SB (1999) A neural-statistical approach to multitemporal and multisource remote-sensing image classification. IEEE Trans Geosci Remote Sens 37(3):1350–1359CrossRefGoogle Scholar
  38. 38.
    Melgani F (2002) Classification of multitemporal remote-sensing images by a fuzzy fusion of spectral and spatio-temporal contextual information. Int J Pattern Recognit Artif Intell 18(2):143–156CrossRefGoogle Scholar
  39. 39.
    Melgani F, Serpico SB (2002) A statistical approach to the fusion of the spectral and spatio-temporal contextual information for the classification of remote sensing images. Pattern Recognit Lett 23(9):1053–1061CrossRefGoogle Scholar
  40. 40.
    Conradsen K, Aasbjerg Nielsen A, Schou J, Skriver H (2003) A test statistic in the complex Wishart distribution and its application to change detection in polarimetric SAR data. IEEE Trans Geosci Remote Sens 41(1):4–19CrossRefGoogle Scholar
  41. 41.
    Lombardo P, Macrí Pellizzeri T (2002) Maximum likelihood signal processing techniques to detect a step pattern of change in multitemporal SAR images. IEEE Trans Geosci Remote Sens 40(4):853–870CrossRefGoogle Scholar
  42. 42.
    Singh A (1989) Digital change detection techniques using remotely-sensed data. Int J Remote Sens 10(6):989–1003CrossRefGoogle Scholar
  43. 43.
    Liew SC, Kam S-P, Tuong T-P, Chen P, Minh VQ, Lim H (1998) Application of multitemporal ERS-1 synthetic aperture radar in delineating rice cropping systems in the Mekong River Delta, Vietnam. IEEE Trans Geosci Remote Sens 36(5):1412–1420CrossRefGoogle Scholar
  44. 44.
    Dierking W, Skriver H (2002) Change detection for thematic mapping by means of airborne multitemporal polarimetric SAR imagery. IEEE Trans Geosci Remote Sens 40(3):618–636CrossRefGoogle Scholar
  45. 45.
    Rosin P (2002) Thresholding for change detection. Computer Vis Image Underst 86(2):79–95CrossRefGoogle Scholar
  46. 46.
    Rosin P, Ioannidis E (2003) Evaluation of global image thresholding for change detection, Pattern Recognit Lett 24(14):2345–2356CrossRefGoogle Scholar
  47. 47.
    Smits P, Annoni A (2000) Toward specification-driven change detection. IEEE Tran Geosci Remote Sens 38(3):1484–1488CrossRefGoogle Scholar
  48. 48.
    Poor HV (1994) An introduction to signal detection and estimation, 2nd edn. Springer, New YorkGoogle Scholar
  49. 49.
    Kay SM (1993) Fundamentals of statistical signal processing: detection theory. Prentice-Hall, Upper Saddle River, NJGoogle Scholar
  50. 50.
    Moser G, Serpico SB (2006) Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery. IEEE Trans Geosci Remote Sens 44(10):2972–2982CrossRefGoogle Scholar
  51. 51.
    Melgani F, Moser G, Serpico SB (2002) Unsupervised change detection methods for remote sensing images. Opt Eng 41(12):3288–3297CrossRefGoogle Scholar
  52. 52.
    Moser G, Melgani F, Serpico SB (2003) Advances in unsupervised change detection. In: Chen CH (ed) Frontiers of remote sensing information processing. World Scientific, SingaporeGoogle Scholar
  53. 53.
    Bruzzone L, Prieto DF (2000) Automatic analysis of the difference image for unsupervised change detection. IEEE Trans Geosci Remote Sens 38(3):1171–1182CrossRefGoogle Scholar
  54. 54.
    Bruzzone L, Prieto DF (2002) An adaptive semiparametric and context-based approach to unsupervised change detection in multitemporal remote-sensing images. IEEE Trans Image Process 11(4):452–466PubMedCrossRefGoogle Scholar
  55. 55.
    Colwell JE, Weber FP (1981) Forest change detection. In: Proceeding of the 15th international symposium on remote sensing of environment, pp 839–852Google Scholar
  56. 56.
    Malila WA (1980) Change vector analysis: an approach for detecting forest changes with Landsat. In: Proceeding of the 6th annual symposium on machine processing of remotely sensed data, pp 326–335Google Scholar
  57. 57.
    Di Stefano L, Mattoccia S, Mola M (2003) A change-detection algorithm based on structure and colour. In: IEEE conference on advanced video and signal-based surveillance 2003, pp 252–259Google Scholar
  58. 58.
    Sakuma S, Nakanishi T, Takahashi Y, Fujino Y, Ohtsuka S, Tomono A, Nakanishi N, Tsubouchi T, Tanino T (2006) Image registration, color correction, and change detection based on value of difference in sequential ocular fundus images. Syst Comput Jpn 37(11):100–112CrossRefGoogle Scholar
  59. 59.
    Berger JW, Patel TR, Shin DS, Piltz JR, Stone RA (2000) Computerized stereo chronoscopy and alternation flicker to detect optic nerve head contour change. Ophthalmology 107(7):1316–1320PubMedCrossRefGoogle Scholar
  60. 60.
    Cree MJ, Olson JA, McHardy KC, Sharp PF, Forrester JV (1999) The preprocessing of retinal images for the detection of Fluorescein leakage. Phys Med Biol 44:293–308PubMedCrossRefGoogle Scholar
  61. 61.
    Goatman KA, Cree MJ, Olson JA, Forrester JV, Sharp PF (2003) Automated measurement of microaneurysm turnover. Invest Ophthalmol Vis Sci 44:5335–5341PubMedCrossRefGoogle Scholar
  62. 62.
    Sbeh ZB, Cohen LD, Mimoun G, Coscas G (2001) A new approach of geodesic reconstruction for drusen segmentation in eye fundus images. IEEE Trans Med Imaging 20(12):1321–1333PubMedCrossRefGoogle Scholar
  63. 63.
    Narasimha-Iyer H, Can A, Roysam B, Stewart CV, Tanenbaum HL, Majerovics A, Singh H (2006) Robust detection and classification of longitudinal changes in color retinal fundus images for monitoring diabetic retinopathy. IEEE Trans Biomed Eng 53(6):1084–1098PubMedCrossRefGoogle Scholar
  64. 64.
    Narasimha-Iyer H, Can A, Roysam B, Tanenbaum HL, Majerovics A (2007) Integrated analysis of vascular and non-vascular changes from color retinal fundus image sequences. IEEE Trans Biomed Eng 54(8):1436–1445PubMedCrossRefGoogle Scholar
  65. 65.
    Rayner KE (1992) Eye movements and visual cognition: scene perception and reading, 2nd edn. Springer, New YorkGoogle Scholar
  66. 66.
    Serra J (1982) Image analysis and mathematical morphology. Academic, LondonGoogle Scholar
  67. 67.
    Chanussot J, Mauris G, Lambert P (1999) Fuzzy fusion techniques for linear features detection in multitemporal SAR images. IEEE Trans Geosci Remote Sens 37(3):1292–1305CrossRefGoogle Scholar
  68. 68.
    Troglio G, Benediktsson JA, Serpico SB, Moser G, Karlsson RA, Halldorsson GH, Stefansson E (2008) Automatic registration of retina images based on genetic techniques. In: Proceeding of the IEEE engineering for medicine and biology conference, pp 5419–5424Google Scholar
  69. 69.
    Michalewicz Z (1999) Genetic algorithms + data structures = evolution programs, 3rd edn. Springer, Berlin, GermanyGoogle Scholar
  70. 70.
    Bruzzone L, Cossu R (2002) Analysis of multitemporal remote-sensing images for change detection: Bayesian thresholding approaches. In: Chen CH, Binaghi E, Brivio PA, Serpico SB (eds) Geospatial pattern recognition, Alphen aan den Rijn, Netherlands, pp 203–230Google Scholar
  71. 71.
    Akita K, Kuga H (1982) A computer method of understanding ocular fundus images. Pattern Recognit 15(6):431–443CrossRefGoogle Scholar
  72. 72.
    Sinthanayothin C, Boyce JF, Cook HL, Williamson TH (1999) Automated localisation of the optic disc, fovea, and retinal blood vessels from digital color fundus images. Br J Ophthalmol 83(8):902–910PubMedCrossRefGoogle Scholar
  73. 73.
    Chi Z, Yan H, Pham T (1996) Fuzzy algorithms: with applications to image processing and pattern recognition. World Scientific Publishing, SingaporeCrossRefGoogle Scholar
  74. 74.
    Huang L-K, Wang M-JJ (1995) Image thresholding by minimizing the measures of fuzziness. Pattern Recognit 28(1):41–51CrossRefGoogle Scholar
  75. 75.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66CrossRefGoogle Scholar
  76. 76.
    Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New YorkGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Giulia Troglio
    • 1
    • 2
    Email author
  • Jon Atli Benediktsson
  • Gabriele Moser
  • Sebastiano Bruno Serpico
  • Einar Stefansson
  1. 1.Faculty of Electrical and Computer EngineeringUniversity of IcelandReykjavikIceland
  2. 2.Department of Biophysical and Electronic EngineeringUniversity of GenoaGenoaItaly

Personalised recommendations