Advertisement

Automatic Differentiation of u- and n-serrated Patterns in Direct Immunofluorescence Images

  • Chenyu ShiEmail author
  • Jiapan Guo
  • George Azzopardi
  • Joost M. Meijer
  • Marcel F. Jonkman
  • Nicolai Petkov
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9256)

Abstract

Epidermolysis bullosa acquisita (EBA) is a subepidermal autoimmune blistering disease of the skin. Manual u- and n-serrated patterns analysis in direct immunofluorescence (DIF) images is used in medical practice to differentiate EBA from other forms of pemphigoid. The manual analysis of serration patterns in DIF images is very challenging, mainly due to noise and lack of training of the immunofluorescence (IF) microscopists. There are no automatic techniques to distinguish these two types of serration patterns. We propose an algorithm for the automatic recognition of such a disease. We first locate a region where u- and n-serrated patterns are typically found. Then, we apply a bank of B-COSFIRE filters to the identified region of interest in the DIF image in order to detect ridge contours. This is followed by the construction of a normalized histogram of orientations. Finally, we classify an image by using the nearest neighbors algorithm that compares its normalized histogram of orientations with all the images in the dataset. The best results that we achieve on the UMCG publicly available data set is \(84.6\%\) correct classification, which is comparable to the results of medical experts.

Keywords

Serration patterns analysis Direct immunofluorescence image COSFIRE filter Ridge detection Skin disease 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Azzopardi, G., Petkov, N.: A CORF computational model of a simple cell that relies on LGN input outperforms the Gabor function model. Biological Cybernetics 106(3), 177–189 (2012)CrossRefGoogle Scholar
  2. 2.
    Azzopardi, G., Petkov, N.: Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 35(2), 490–503 (2013)CrossRefGoogle Scholar
  3. 3.
    Azzopardi, G., Strisciuglio, N., Vento, M., Petkov, N.: Trainable COSFIRE filters for vessel delineation with application to retinal images. Medical Image Analysis 19(1), 46–57 (2015)CrossRefGoogle Scholar
  4. 4.
    Buijsrogge, J.J.A., Diercks, G.F.H., Pas, H.H., Jonkman, M.F.: The many faces of epidermolysis bullosa acquisita after serration pattern analysis by direct immunofluorescence microscopy. British Journal of Dermatology 165(1), 92–98 (2011)CrossRefGoogle Scholar
  5. 5.
    Canny, J.: A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(6), 679–698 (1986)CrossRefGoogle Scholar
  6. 6.
    Gammon, W., Kowalewski, C., Chorzelski, T., Kumar, V., Briggaman, R., Beutner, E.: Direct immunofluorescence studies of sodium chloride-separated skin in the differential diagnosis of bullous pemphigoid and epidermolysis bullosa acquisita. Journal of the American Academy of Dermatology 22(4), 664–670 (1990)CrossRefGoogle Scholar
  7. 7.
    Petkov, N.: Biologically motivated computationally intensive approaches to image pattern-recognition. Future Generation Computer Systems 11(4–5), 451–465 (1995). 1994 Europe Conference on High Performance Computing and Networking (HPCN Europe 94), Munich, Germany, 1994CrossRefGoogle Scholar
  8. 8.
    Petkov, N., Kruizinga, P.: Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: Bar and grating cells. Biological Cybernetics 76(2), 83–96 (1997)CrossRefzbMATHGoogle Scholar
  9. 9.
    Petkov, N., Westenberg, M.: Suppression of contour perception by band-limited noise and its relation to non-classical receptive field inhibition. Biological Cybernetics 88(10), 236–246 (2003)CrossRefzbMATHGoogle Scholar
  10. 10.
    Terra, J.B., Meijer, J.M., Jonkman, M.F., Diercks, G.F.H.: The n- vs. u-serration is a learnable criterion to differentiate pemphigoid from epidermolysis bullosa acquisita in direct immunofluorescence serration pattern analysis. British Journal of Dermatology 169(1), 100–105 (2013)CrossRefGoogle Scholar
  11. 11.
    Terra, J.B., Pas, H.H., Hertl, M., Dikkers, F.G., Kamminga, N., Jonkman, M.F.: Immunofluorescence serration pattern analysis as a diagnostic criterion in antilaminin-332 mucous membrane pemphigoid: immunopathological findings and clinical experience in 10 Dutch patients. British Journal of Dermatology 165(4), 815–822 (2011)CrossRefGoogle Scholar
  12. 12.
    UMCG: UMCG online test (2013). http://www.nversusu.umcg.nl/
  13. 13.
    Vodegel, R., Jonkman, M., Pas, H., De Jong, M.: U-serrated immunodeposition pattern differentiates type VII collagen targeting bullous diseases from other subepidermal bullous autoimmune diseases. British Journal of Dermatology 151(1), 112–118 (2004)CrossRefGoogle Scholar
  14. 14.
    Woodley, D.T., Briggaman, R.A., O’Keefe, E.J., Inman, A.O., Queen, L.L., Gammon, W.R.: Identification of the skin basement-membrane autoantigen in epidermolysis bullosa acquisita. New England Journal of Medicine 310(16), 1007–1013 (1984)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Chenyu Shi
    • 1
    Email author
  • Jiapan Guo
    • 1
  • George Azzopardi
    • 1
    • 2
  • Joost M. Meijer
    • 3
  • Marcel F. Jonkman
    • 3
  • Nicolai Petkov
    • 1
  1. 1.Johann Bernoulli Institute for Mathematics and Computer ScienceUniversity of GroningenGroningenThe Netherlands
  2. 2.Intelligent Computer SystemsUniversity of MaltaMsidaMalta
  3. 3.Dermatology for Medical Sciences, University Medical Center Groningen (UMCG)University of GroningenGroningenThe Netherlands

Personalised recommendations