Texture-Based Polyp Detection in Colonoscopy

  • Stefan Ameling
  • Stephan Wirth
  • Dietrich Paulus
  • Gerard Lacey
  • Fernando Vilarino
Part of the Informatik aktuell book series (INFORMAT)

Abstract

Colonoscopy is one of the best methods for screening colon cancer. A variety of research groups have proposed methods for automatic detection of polyps in colonoscopic images to support the doctors during examination. However, the problem can still not be assumed as solved. The major drawback of many approaches is the amount and quality of images used for classifier training and evaluation. Our database consists of more than four hours of high resolution video from colonoscopies which were examined and labeled by medical experts. We applied four methods of texture feature extraction based on Grey-Level-Co-occurence and Local-Binary-Patterns. Using this data, we achieved classification results with an area under the ROC-curve of up to 0.96.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    World Health Organization. Media Centre Fact Sheet No 297: Cancer; 2006 [cited 2008 Oct 04]. [online]. Available from: http://www.who.int/mediacentre/factsheets/fs297/en/print.html.Google Scholar
  2. 2.
    Thomson A, Ahnen D, Riopelle J. Intestinal polypoid adenomas. eMedicine, The Continually Updated Clinical Reference. 2007;Available from: http://www.emedicine.com/med/TOPIC1175.HTM.Google Scholar
  3. 3.
    Iakovidis DK, Maroulis DE, Karkanis SA. An intelligent system for automatic detection of gastrointestinal adenomas in video endoscopy. Comput Biol Med. 2006;36(10):1084–1103.CrossRefGoogle Scholar
  4. 4.
    Karkanis SA, Iakovidis DK, Karras DA, et al. Detection of lesions in endoscopic video using textural descriptors on wavelet domain supported by artificial neural network architectures. Proc IEEE Conf Image Proc. 2001; p. 833–836.Google Scholar
  5. 5.
    Wang P, Krishnan SM, Kugean C, et al. Classification of endoscopic images based on texture and neural network. Proc IEEE EMBS. 2001;4:3691–3695.Google Scholar
  6. 6.
    Ameling S, Wirth S, Paulus D. Methods for Polyp Detection in Colonoscopy Videos: A Review. University of Koblenz-Landau; 2008. 14/2008.Google Scholar
  7. 7.
    Shevchenko N, Mühldorfer S, Wittenberg T, et al. Untersuchung von Texturanalysemethoden zur automatischen Polypenerkennung. In: 7. Jahrestagung der Deutschen Gesellschaft für Computer-und Roboterassistierte Chirugie e. V., Tagungsband; 2008. p. 205–206.Google Scholar
  8. 8.
    Vilarino F, Lacey G, Zhou J, et al. Automatic labeling of colonoscopy video for cancer detection. Proc Iberian Conf: Patt Recogn Image Anal. 2007; p. 290–297.Google Scholar
  9. 9.
    Haralick RM, Dinstein I, Shanmugam K. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;3(6):610–621.CrossRefGoogle Scholar
  10. 10.
    Pietikainen M, Ojala T. Nonparametric texture analysis with complementary spatial operators. Texture Analysis in Machine Vision, Series in Machine Perception and Artificial Intelligence. 2000;40.Google Scholar
  11. 11.
    Mäenpää T. The local binary pattern approach to texture analysis-extensions and applications; 2003. Ph.D. thesis, University of Oulu.Google Scholar
  12. 12.
    Vapnik V. The Nature of Statistical Learning Theory. Springer; 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Stefan Ameling
    • 1
  • Stephan Wirth
    • 1
  • Dietrich Paulus
    • 1
  • Gerard Lacey
    • 2
  • Fernando Vilarino
    • 2
  1. 1.Institute for Computational VisualisticsUniversity of Koblenz-LandauGermany
  2. 2.Department of Computer ScienceTrinity College DublinIreland

Personalised recommendations