A Markov Random Field Approach to Outline Lesions in Fundus Images

  • E. Grisan
  • A. Ruggeri
Part of the IFMBE Proceedings book series (IFMBE, volume 22)

Abstract

Due to its blood microcirculation, the retina is one of the first organs affected by hypertension and diabetes: retinal damages can lead to serious visual loss, that can be avoided by an early diagnosis. The most distinctive sign of diabetic retinopathy or severe hypertensive retinopathy are dark lesions such as haemorrhages and microaneurysms (HM), and bright lesions such as hard exudates (HE) and cotton wool spots (CWS). Automatic detection of their presence in the retina is thus of paramount importance for assessing the presence of retinopathy, and therefore relieve the burden of image examination by retinal experts. The first step for the automatic detection of retinal lesions has to identify candidate lesions, not losing any of them, and providing with accurate outlines, so to allow the extraction of meaningful features for a possible subsequent classification. To accomplish this, we propose a two stage approach. The first stage identifies the rough location of candidate lesions with one or more seed points, evaluating a measure of the spatial density of pixels selected by a local thresholding. The second stage has the objective of outlining as accurately as possible the lesions surrounding each seed. Due to the high variability of lesions and background appearance, classical region growing approaches often fail and are difficult to calibrate, since in retinal imaging the noisy and highly variable background hides the small homogenous regions representing lesions. To tackle this, we rely on a stochastic modelling of a region of interest around a seed as a Markov random field: This is particularly suited to separate objects with different textures, since it combines feature distribution and spatial connectivity. Responses to a Gabor filters bank spanning different orientations and scales provide the description of the local texture, and the final classification is obtained via a simulated annealing optimization. Along with the classification, we propose a simple post-optimization measure to discard regions where no lesions are present despite the presence of seeds. We show results of the proposed method on a data set of manually segmented 60 images, 6 of which containing retinal lesions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    G. E. Øien and P. Osnes. Diabetic retinopathy: Automatic detection of early symptoms from retinal images. In Proceedings NORSIG-95 Norwegian Signal Processing Symposium, September 1995.Google Scholar
  2. [2]
    G. Yang, L. Gagnon, S. Wang, and M. C. Boucher. Algorithm for detecting Micro-Aneurysms in low resolution color retinal images. In Proceedings of Vision Interface 2001, Ottawa, pages 265–271, June 2001.Google Scholar
  3. [3]
    E. Grisan and A. Ruggeri. A hierarchical bayesian classification for non-vascular lesions detection in fundus images. In EMBEC’05, 3rd EuropeanMedical and Biological Enginerring Conference, Prague (CZ), November 2005.Google Scholar
  4. [4]
    M. Niemeijer, B. van Ginneken, J.J. Staal, M.S.A. Suttorp-Schulten, and M.D. Abramoff. Automatic detection of red lesions in digital color fundus photographs. IEEE Transactions on Medical Imaging, 24:584–592, 2005.CrossRefGoogle Scholar
  5. [5]
    Y. Deng and B. Manjunath. Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. Pattern Anal.Mach. Intell., 23(8):800–810, 2001.CrossRefGoogle Scholar
  6. [6]
    H. D. Cheng, X. H. Jiang, and J. Wang. Color imnage segmentation based on homogram thresholding and region merging. Pattern recognition, 35(2):373–393, February 2002.MATHCrossRefGoogle Scholar
  7. [7]
    L. Macaire, N. Vandenbroucke, and J.-G. Postaire. Color image segmentation by analysis of subset connectedness and color homogeneity properties. Computer Vision and Image Understanding, 102(1):105–116, 2002.CrossRefGoogle Scholar
  8. [8]
    E. Grisan and A. Ruggeri. Segmentation of candidate dark lesions in fundus images based on local thresholding and colour density. In 29th IEEE EMBS Annual International Conference, Lyon (F), August 2007.Google Scholar
  9. [9]
    G.R. Cross and A.K. Jain. Markov random fields texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5:25–38, 1983.CrossRefGoogle Scholar
  10. [10]
    S. Geman and D. Geman. Stochastic relaxation, gibbs distribution and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984.Google Scholar
  11. [11]
    H. Deng and D. A. Clausi. Gaussian MRF rotation-invariant features for image classification. IEEE Transactions on Pattern Recognition and MAchine Intelligence, 26(7):951–955, July 2004.CrossRefGoogle Scholar
  12. [12]
    A. Hoover, V. Kouznestova, and M. Goldbaum. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Transactions on Medical Imaging, 19(3):203–210, March 2000.CrossRefGoogle Scholar
  13. [13]
    E. Grisan, A. Pesce, A. Giani, M. Foracchia, and A. Ruggeri. A new tracking system for the robust extraction of retinal vessel structure. In The 26th International Conference of the IEEE Engineering in Medicine and Biology Society, September 2004.Google Scholar
  14. [14]
    Huiqi Li and O. Chutatape. A model-based approach for automated feature extraction in fundus images. In Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV 2003), pages 394–399. IEEE Computer Society, October 2003.Google Scholar
  15. [15]
    T. Walter, J.-C. Klein, P. Masin, and A. Erginay. A contribution of image processing to the diagnosis of diabetic retinopathy — detection of exufdates in color fundus images of the human retina. IEEE Transactions on Medical Imaging, 21(10):1236–1243, October 2002.CrossRefGoogle Scholar
  16. [16]
    M. Foracchia, E. Grisan, and A. Ruggeri. Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE Transactions on Medical Imaging, 23(10):1189–1195, October 2004.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • E. Grisan
    • 1
  • A. Ruggeri
    • 1
  1. 1.Department of Information EngineeringUniversity of PadovaItaly

Personalised recommendations