Non-negative Matrix Factorization for Endoscopic Video Summarization

  • Spyros Tsevas
  • Dimitris Iakovidis
  • Dimitris Maroulis
  • Emmanuel Pavlakis
  • Andreas Polydorou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5138)


Wireless Capsule Endoscopy (WCE) has been introduced as a non-invasive colour imaging technique for the inspection of the small intestin along with the rest of the gastrointestinal tract. Each WCE examination results in a 50,000-frames video that has to be visually inspected frame-by-frame by the doctor and this may be a highly time-consuming task even for the experienced gastroenterologist. In this paper we propose a novel approach that leads to a summarized version of the original video enabling significant reduction in the video assessment time without losing any critical information. It is based on symmetric non-negative matrix factorisation initialized by the fuzzy c-means algorithm and it is supported by non-negative Lagrangian relaxation to extract a subset of video frames containing the most representative scenes from an entire examination. The experimental evaluation of the proposed approach was performed using previously annotated endoscopic videos from various sites of the small intestine.


Non-negative matrix factorisation wireless capsule endoscopy video summarisation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Iddan, G., Meron, G., Glukhovsky, A., Swain, P.: Wireless capsule endoscopy. Nature 405 (6785), 417–418 (2000)CrossRefGoogle Scholar
  2. 2.
    Maieron, A., Hubner, D., Blaha, B., Deutsch, C., Schickmair, T., Ziachehabi, A., Kerstan, E., Knoflach, P., Schoefl, R.: Multicenter retrospective evaluation of capsule endoscopy in clinical routine. Endoscopy 36(10), 864–868 (2004)CrossRefGoogle Scholar
  3. 3.
    Coimbra, M.T., Cunha, J.P.S.: MPEG-7 visual descriptors - contributions for automated feature extraction in capsule endoscopy. IEEE Transactions on Circuits and Systems for Video Technology 16(5), 628–636 (2006)CrossRefGoogle Scholar
  4. 4.
    Li, B., Meng, M.Q.-H.: Analysis of the gastrointestinal status from wireless capsule endoscopy images using local color feature. In: ICIA 2007 International Conference on Information Acquisition, July 8-11, 2007, pp. 553–557 (2007)Google Scholar
  5. 5.
    Mackiewicz, M., Berens, J., Fisher, M., Bell, D.: Colour and texture based gastrointestinal tissue discrimination. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2, pp. II597-II600 (2006)Google Scholar
  6. 6.
    Berens, J., Mackiewicz, M., Bell, D.: Stomach, intestine and colon tissue discriminators for wireless capsule endoscopy images. In: Progress in Biomedical Optics and Imaging, Proceedings of SPIE, vol. 5747, pp. (I): 283–290 (2005)Google Scholar
  7. 7.
    Lee, J., Oh, J., Shah, S.K., Yuan, X., Tang, S.J.: Automatic classification of digestive organs in wireless capsule endoscopy videos. In: Proceedings of the ACM, Symposium on Applied Computing, pp. 1041–1045 (2007)Google Scholar
  8. 8.
    Bourbakis, N.: Detecting abnormal patterns in WCE images. In: Proceedings - BIBE 2005, 5th IEEE Symposium on Bioinformatics and Bioengineering, pp. 232–238 (2005)Google Scholar
  9. 9.
    Hwang, S., Oh, J., Cox, J., Tang, S.J., Tibbals, H.F.: Blood detection in wireless capsule endoscopy using expectation maximization clustering. In: Progress in Biomedical Optics and Imaging, Proceedings of SPIE, vol. 6144 I (2006)Google Scholar
  10. 10.
    Kodogiannis, V.S., Boulougoura, M.: Neural network-based approach for the classification of wireless-capsule endoscopic images. In: Proceedings of the International Joint Conference on Neural Networks, vol. 4, pp. 2423–2428 (2005)Google Scholar
  11. 11.
    Kodogiannis, V.S., Boulougoura, M., Lygouras, J.N., Petrounias, I.: A neuro-fuzzy-based system for detecting abnormal patterns in wireless-capsule endoscopic images. Neurocomputing 70(4-6), 704–717 (2007)Google Scholar
  12. 12.
    Li, B., Meng, M.Q.-H.: Wireless capsule endoscopy images enhancement by tensor based diffusion. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Proceedings, pp. 4861–4864 (2006)Google Scholar
  13. 13.
    Vilariño, F., Kuncheva, L.I., Radeva, P.: ROC curves and video analysis optimization in intestinal capsule endoscopy. Pattern Recognition Letters 27(8), 875–881 (2006)CrossRefGoogle Scholar
  14. 14.
    Vilariño, F., Spyridonos, P., Pujol, O., Vitrià, J., Radeva, P., De Iorio, F.: Automatic detection of intestinal juices in wireless capsule video endoscopy. In: Proceedings - International Conference on Pattern Recognition, vol. 4, pp. 719–722 (2006)Google Scholar
  15. 15.
    Vilariño, F., Spyridonos, P., Vitrià, J., Malagelada, C., Radeva, P.: A machine learning framework using SOMs: Applications in the intestinal motility assessment. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS(LNAI), vol. 4225, pp. 188–197. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  16. 16.
    Wadge, E., Boulougoura, M., Kodogiannis, V.: Computer-assisted diagnosis of wireless-capsule endoscopic images using neural network based techniques. In: Proceedings of the 2005 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, CIMSA 2005, pp. 328–333 (2005)Google Scholar
  17. 17.
    Okun, O., Priisalu, H.: Unsupervised data reduction. Signal Processing 87(9), 2260–2267 (2007)CrossRefGoogle Scholar
  18. 18.
    Lee, D.D., Seung, H.S.: Unsupervised learning by convex and conic coding. Adv. Neural Inf. Process. Systems 9, 515–521 (1997)Google Scholar
  19. 19.
    Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401, 788–791 (1999)CrossRefGoogle Scholar
  20. 20.
    Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. Adv. Neural Inf. Process. Systems 13, 556–562 (2000)Google Scholar
  21. 21.
    Saul, L.K., Lee, D.D.: Multiplicative updates for classification by mixture models. Adv. Neural Inf. Process. Systems 14, 897–904 (2002)Google Scholar
  22. 22.
    Ding, C., He, X., Simon, H.D.: On the equivalence of nonnegative matrix factorization and spectral clustering. In: Proceedings of the SIAM International Conference on Data Mining, Newport Beach, CA, April 2005, pp. 606–610 (2005)Google Scholar
  23. 23.
    Ding, C., He, X., Simon, H.D.: Nonnegative Lagrangian relaxation of K-means and spectral clustering. In: Proceedings of the Sixteenth European Conference on Machine Learning, Porto, Portugal, October 3–7, 2005, pp. 530–538 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Spyros Tsevas
    • 1
  • Dimitris Iakovidis
    • 1
  • Dimitris Maroulis
    • 1
  • Emmanuel Pavlakis
    • 2
  • Andreas Polydorou
    • 2
  1. 1.Dept. of Informatics and TelecommunicationsUniversity of Athens, PanepistimiopolisAthensGreece
  2. 2.Department of SurgeryAretaieion HospitalAthensGreece

Personalised recommendations