Quantitative color analysis for capillaroscopy image segmentation

  • Michela Goffredo
  • Maurizio Schmid
  • Silvia Conforto
  • Beatrice Amorosi
  • Tommaso D’Alessio
  • Claudio Palma
Original Article

Abstract

This communication introduces a novel approach for quantitatively evaluating the role of color space decomposition in digital nailfold capillaroscopy analysis. It is clinically recognized that any alterations of the capillary pattern, at the periungual skin region, are directly related to dermatologic and rheumatic diseases. The proposed algorithm for the segmentation of digital capillaroscopy images is optimized with respect to the choice of the color space and the contrast variation. Since the color space is a critical factor for segmenting low-contrast images, an exhaustive comparison between different color channels is conducted and a novel color channel combination is presented. Results from images of 15 healthy subjects are compared with annotated data, i.e. selected images approved by clinicians. By comparison, a set of figures of merit, which highlights the algorithm capability to correctly segment capillaries, their shape and their number, is extracted. Experimental tests depict that the optimized procedure for capillaries segmentation, based on a novel color channel combination, presents values of average accuracy higher than 0.8, and extracts capillaries whose shape and granularity are acceptable. The obtained results are particularly encouraging for future developments on the classification of capillary patterns with respect to dermatologic and rheumatic diseases.

Keywords

Capillaroscopy Segmentation Color analysis Color space 

References

  1. 1.
    Alonso F, Algorri M, FIores-Mangas F (2004) Composite index for the quantitative evaluation of image segmentation results. In: Engineering in Medicine and Biology Society, 2004. IEMBS ‘04. 26th Annual International Conference of the IEEE, San Francisco, pp 1794–1797Google Scholar
  2. 2.
    Bezemer R, Dobbe JG, Bartels SA, Christiaan Boerma E, Elbers PW, Heger M, Ince C (2011) Rapid automatic assessment of microvascular density in sidestream dark field images. Med Biol Eng Comput 49(11):1269–1278PubMedCrossRefGoogle Scholar
  3. 3.
    Bollinger A, Flagrell B (1990) Clinical capillaroscopy—a guide to its use in clinical research and practice. Hogrefe Huber, Toronto and LewistonGoogle Scholar
  4. 4.
    Cardenes R, De Luis-Garcia R, Bach-Cuadram M (2009) A multidimensional segmentation evaluation for medical image data. Comput Methods Programs Biomed 96(2):108–124PubMedCrossRefGoogle Scholar
  5. 5.
    Chia-Hsien W, Tsu-Yi H, Wei-Duen L, Joung-Liang L, Der-Yuan C, Kuan-Ching L (2008) A novel method for classification of high-resolution nailfold capillary microscopy images. In: First IEEE International Conference on Ubi-Media Computing, pp 513–518Google Scholar
  6. 6.
    Chia-Hsien W, Wei-Duen L, Kuan-Ching L (2007) Classification framework for nailfold capillary microscopy images. In: IEEE Region 10 Conference TENCON 2007, pp 1–4Google Scholar
  7. 7.
    Cutolo M, Pizzorni C, Secchi M, Sulli A (2008) Capillaroscopy. Best Pract Res Clin Rheumatol 22(6):1093–1108PubMedCrossRefGoogle Scholar
  8. 8.
    Cutolo M, Sulli A, Pizzorni C, Accardo S (2000) Nailfold videocapillaroscopy assessment of microvascular damage in systemic sclerosis. J Rheumatol 27:155–160PubMedGoogle Scholar
  9. 9.
    De Visser M, Emslie-Smith A, Engel A (1989) Early ultrastructural alterations in adult dermatomyositis: capillary abnormalities precede other structural changes in muscle. J Neurol Sci 94:1CrossRefGoogle Scholar
  10. 10.
    Dobbe JG, Streekstra GJ, Atasever B, van Zijderveld R, Ince C (2008) Measurement of functional microcirculatory geometry and velocity distributions using automated image analysis. Med Biol Eng Comput 46(7):659–670PubMedCrossRefGoogle Scholar
  11. 11.
    Fang G, Kwok N (2009) Image segmentation using adaptively selected color space. In: 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp 1838–1843Google Scholar
  12. 12.
    Farid H (2001) Blind inverse gamma correction. IEEE Trans Image Process 10(10):1428–1433PubMedCrossRefGoogle Scholar
  13. 13.
    Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861–874CrossRefGoogle Scholar
  14. 14.
    Gibson WC, Bosley HJSGR (1956) Photomicrographic studies of the nailbed capillary networks in human control subjects. J Nerv Ment Dis 219:219–231Google Scholar
  15. 15.
    Goffredo M, Schmid M, Conforto S, Carli M, Neri A, D’Alessio T (2009) Markerless human motion analysis in Gauss-Laguerre transform domain: an application to sit-to-stand in young and elderly people. IEEE Trans Inf Technol Biomed 13(2):207–216PubMedCrossRefGoogle Scholar
  16. 16.
    Goffredo M, Schmid M, Conforto S, D’Alessio T (2005) A markerless sub-pixel motion estimation technique to reconstruct kinematics and estimate the centre of mass in posturography. Med Eng Phys 28(7):719–726PubMedCrossRefGoogle Scholar
  17. 17.
    Gudmundsson M, El-Kwae E, Kabuka M (1998) Edge detection in medical images using a genetic algorithm. IEEE Trans Med Imaging 17(3):469–474PubMedCrossRefGoogle Scholar
  18. 18.
    Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36PubMedGoogle Scholar
  19. 19.
    Hu Q, Mahler F (1999) New system for image analysis in nailfold capillaroscopy. Microcirculation 6:227–235PubMedGoogle Scholar
  20. 20.
    Jones B, Oral M, Morris C, Ring EFJ (2001) A proposed taxonomy for nailfold capillaries based on their morphology. IEEE Trans Med Imaging 20(4):333–341PubMedCrossRefGoogle Scholar
  21. 21.
    Kabasakal Y, Elvins D, Ring E, McHugh N (1996) Quantitative nailfold capillaroscopy findings in a population with connective tissue disease and in normal healthy controls. Ann Rheum Dis 55:507–512PubMedCrossRefGoogle Scholar
  22. 22.
    Kwasnicka H, Paradowski M (2007) Capillaroscopy image analysis as an automatic image annotation problem. In: 6th International Conference on Computer Information Systems and Industrial Management Applications, pp 266–27Google Scholar
  23. 23.
    Kwok N, Ha Q, Fang G (2009) Effect of color space on color image segmentation. CISP ‘09. In: 2nd International Congress on Image and Signal Processing, pp 1–5Google Scholar
  24. 24.
    Lee P, Leung F, Alderdice C, Armstrong S (1983) Nailfold capillary microscopy in the connective tissue diseases: a semiquantitative assessment. J Rheumatol 10(6):930–938PubMedGoogle Scholar
  25. 25.
    Maricq HR, Maize JC (1982) Nailfold capillary abnormalities. Clin Rheum Dis 8(2):455–478Google Scholar
  26. 26.
    Maricq M (1988) Raynauds phenomenon and microvascular abnormalities in scleroderma (systemic sclerosis). In: Black MJ (ed) Systemic sclerosis: scleroderma, pp 151–66Google Scholar
  27. 27.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66CrossRefGoogle Scholar
  28. 28.
    Paradowski M, Kwasnicka H, Borysewicz K (2009) Avascular area detection in nailfold capillary images. In: International Multiconference on Computer Science and Information Technology, IMCSIT ‘09, pp 419–424Google Scholar
  29. 29.
    Pichon E, Tannenbaum A, Kikinis R (2004) A statistically based flow for image segmentation. Med Image Anal 8(3):267–274Google Scholar
  30. 30.
    Pratt WK (1978) Digital image processing. Wiley, New YorkGoogle Scholar
  31. 31.
    Riao-Rojas J, Prieto-Ortiz F, Morantes L, Sanchez-Camperos E, Jaramillo-Ayerbe F (2007) Segmentation and extraction of morphologic features from capillary images. Sixth Mexican International Conference on Artificial Intelligence—Special Session, MICAI 2007, pp 148–159Google Scholar
  32. 32.
    Rouen LR, Terry EN, Doft BH, Redisch W (1972) Classification and measurement of surface microvessels in man. Microvasc Res 4:285–292PubMedCrossRefGoogle Scholar
  33. 33.
    Tanimoto T (1958) An elementary mathematical theory of classification and prediction. IBM internal rep, New YorkGoogle Scholar
  34. 34.
    Wang Yuedong XH (2009) Studies on color space selection and methods of segmentation quality evaluation. In: 1st International Conference on Information Science and Engineering (ICISE), pp 1437–1440Google Scholar
  35. 35.
    Wesolkowski S, Jernigan M, Dony R (2000) Comparison of color image edge detectors in multiple color spaces. In: International Conference on Image Processing, vol 2, pp 796–799Google Scholar
  36. 36.
    Zhang Y (1996) A survey on evaluation methods for image segmentation. Pattern Recognit 29(8):1335–1346CrossRefGoogle Scholar
  37. 37.
    Zhanwu X, Miaoliang Z (2006) Color-based skin detection: survey and evaluation. In: Proceedings of the 12th International Conference on Multi-Media Modelling, vol 10, BeijingGoogle Scholar
  38. 38.
    Zhong J, Asker CL, Salerud EG (2000) Imaging, image processing and pattern analysis of skin capillary ensembles. Skin Res Technol 6:45–57PubMedCrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2012

Authors and Affiliations

  • Michela Goffredo
    • 1
  • Maurizio Schmid
    • 1
  • Silvia Conforto
    • 1
  • Beatrice Amorosi
    • 2
  • Tommaso D’Alessio
    • 1
  • Claudio Palma
    • 3
  1. 1.Department of Applied ElectronicsUniversity “Roma TRE”RomeItaly
  2. 2.IFO San Gallicano Dermatology Institute, IRCCSRomeItaly
  3. 3.Department of PhysicsUniversity “Roma TRE”RomeItaly

Personalised recommendations