Automated Recognition of Abnormal Structures in WCE Images Based on Texture Most Discriminative Descriptors

  • Piotr Szczypiński
  • Artur Klepaczko
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 84)


In this paper we study the problem of classification of wireless capsule endoscopy images (WCE). We aim at developing a computer system that would aid in medical diagnosis procedure. The goal is to automatically detect images showing pathological alterations in an 8-hour-long WCE video. We focus on three classes of pathologies, ulcers, bleedings and petechia, since they are typical for several diseases of intestines. Utilized are methods for image texture and color analysis to obtain numerical description of images. Then, three methods for selection of most discriminative descriptors are used, namely Vector Supported Convex Hull, Support Vector Machines and Radial Basis Function Networks. The results produced by the three methods are compared.


Support Vector Machine Convex Hull Feature Subset Radial Basis Function Network Capsule Endoscopy Video 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barber, C., Dobkin, D., Huhdanpaa, H.: The quickhull algorithm for convex hulls. The Quickhull algorithm for convex hulls 22(4), 469–483Google Scholar
  2. 2.
    Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. Artiffcial Intelligence 97, 245–271 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Coimbra, M., Campos, P., Cunha, J.: Extracting clinical information from endoscopic capsule exams using mpeg-7 visual descriptors. In: Integration of Knowledge, Semantics and Digital Media Technology, EWIMT 2005, pp. 105–110 (2005)Google Scholar
  4. 4.
    Coimbra, M., Cunha, J.: Mpeg-7 visual descriptors-contributions for automated feature extraction in capsule endoscopy. IEEE Transactions on Circuits and Systems for Video Technolog 16(5), 628–637 (2006)CrossRefGoogle Scholar
  5. 5.
    Haralick, R.: Statistical and structural approaches to texture. IEEE Proceedings 67(5), 768–804 (1979)CrossRefGoogle Scholar
  6. 6.
    Iddan, G., Meron, G., Glukhowsky, A., Swain, P.: Wireless capsule endoscopy. Nature 405(6785), 417–418 (2000)CrossRefGoogle Scholar
  7. 7.
    Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artiffcial Intelligence 97, 273–324 (1997)zbMATHCrossRefGoogle Scholar
  8. 8.
    Li, B., Meng, M.H.: Ulcer recognition in capsule endoscopy images by texture features. In: 7th World Congress on Intelligent Control and Automation, WCICA 2008, pp. 234–239 (2008)Google Scholar
  9. 9.
    Mackiewicz, M., Berens, J., Fisher, M.: Wireless capsule endoscopy video segmentation using support vector classiffers and hidden markov. In: Proceedings of the International Conference on Medical Image Understanding and Analyses (2006)Google Scholar
  10. 10.
    Mackiewicz, M., Berens, J., Fisher, M., Bell, G.: Colour and texture based gastrointestinal tissue discrimination. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, vol. 2, pp. 597–600 (2006)Google Scholar
  11. 11.
    Pudil, P., Somol, P.: Current feature selection techniques in statistical pattern recognition. In: Kurzynski, M., Puchala, E., Wozniak, M., Zolnierek, A. (eds.) Computer Recognition Systems, Advances in Sof. Computing, vol. 30, Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Swain, P., Fritscher-Ravens, A.: Role of video endoscopy in managing small bowel disease. GUT 53, 1866–1875 (2004)CrossRefGoogle Scholar
  13. 13.
    Szczypinski, P.: (2009), (visited: May 2010)
  14. 14.
    Szczypinski, P., Klepaczko, A.: Convex hull-based feature selection in application to classification of wireless capsule endoscopic images. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2009. LNCS, vol. 5807, pp. 664–675. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  15. 15.
    Szczypinski, P., Sriram, R.D., Sriram, P., Reddy, D.: A model of deformable rings for interpretation of wireless capsule endoscopic videos. Medical Image Analysis 13(2), 312–324 (2009)CrossRefGoogle Scholar
  16. 16.
    Szczypinski, P., Strzelecki, M., Materka, A., Klepaczko, A.: Mazda - a software package for image texture analysis. Computer Methods and Programs in Biomedicine 94, 66–76 (2009)CrossRefGoogle Scholar
  17. 17.
    Tuceryan, M., Jain, A.: Texture Analysis. In: The Handbook of Pattern Recogntion and Computer Vision, pp. 207–248. World Scientific Publishing Co., Singapore (1998)Google Scholar
  18. 18.
    Vilarinao, F., Kuncheva, L.I., Radeva, P.: Roc curves and video analysis optimization in intestinal capsule endoscopy. Pattern Recogn. Lett. 27(8), 875–881 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Piotr Szczypiński
    • 1
  • Artur Klepaczko
    • 1
  1. 1.Institute of ElectronicsTechnical University of ŁodzŁodz

Personalised recommendations