Building an Image-Based System to Automatically Score Psoriasis

  • David Delgado Gomez
  • Jens Michael Carstensen
  • Bjarne Ersbøll
  • Lone Skov
  • Bo Bang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


Nowadays the medical tracking of dermatological diseases is imprecise. The main reason is the lack of suitable objective methods to evaluate the lesion. The severity of the disease is scored by doctors just through their visual examination. In this work, a system to take accurate images of dermatological lesions has been developed. Mathematical methods can be applied to these images to obtain values that summarize the lesion and help to track its evolution. The system is composed of two elements. A precise image acquisition equipment and a statistical procedure to extract the lesions from the images. The system is tested on patients with the dermatological disease psoriasis. Temporal series of images are taken for each patient and the lesions are automatically extracted. Results indicate that to the images obtained are a good source for obtaining derived variables to track the lesion.


image acquisition camera calibration mixture distribution discriminant analysis E-M algorithm psoriasis 


  1. 1.
    Engstrom N., Hansson F., Hellgren L., Tomas J., Nordin B. Vincent J. and Wahlberg A. Computerized Wound Image Analysis In Pathogenesis of Wound and Biomaterial-Associated Infections. Springer-Verlag p 189–193, 1990.Google Scholar
  2. 2.
    Hansen G., Sparrow E., Kokate J., Leland K., Iaizzo P. Wound Status Evaluation using Color Image Processing IEEE Transactions on Medical Imaging, vol. 16, no. 1 February 1997Google Scholar
  3. 3.
    Marszalec E. Pietikainen M. Online Color Camera Calibration Proceedings of the 12th IAPR International Conference in Pattern Recognition, vol. 1Google Scholar
  4. 4.
    Gutenev A., Skladnev V.N, Varvel D. Acquisition-time image quality control in digital dermatoscopy of skin lesion. Computerized Medical Imaging and graphics 25 (2001) 495–499CrossRefGoogle Scholar
  5. 5.
    Hance G., Umbaugh S., Moss R., Stoecker W. Unsupervised Color Image Segmentation IEEE Engineering in Medicine and Biology, February 1996Google Scholar
  6. 6.
    Umbaugh S, Moss R. Automatic Color Segmentation of Images with Application to Detection of Variegated Coloring in Skin Tumors IEEE Engineering in Medicine and Biology, December 1989Google Scholar
  7. 7.
    Johnson R., Wichern D.,: Applied Multivariated Statistical Analysis. Prentince-Hall, Berlin Heidelberg New York (1995)Google Scholar
  8. 8.
    Taxt T., Hjort L., Eikvik L.: Statistical Classification using a Linear Mixture of two Multinormal Probability Densities. Pattern Recognition Letters.(1991) 12 731–737CrossRefGoogle Scholar
  9. 9.
    Folm-Hansen R.: On Chromatic and Geometrical Calibration. PhD tesis, Lyngby (1999)Google Scholar
  10. 10.
    Hastie T., Tibshirani, R., Friedmamn, J.: The Elements of Statistical Learning. SpringerGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • David Delgado Gomez
    • 1
  • Jens Michael Carstensen
    • 1
  • Bjarne Ersbøll
    • 1
  • Lone Skov
    • 2
  • Bo Bang
    • 2
  1. 1.Image processing and computer vision, Informatics and Mathematical ModellingLyngbyDenmark
  2. 2.Department of dermatologyGentofte hospitalHellerupDenmark

Personalised recommendations