Segmentation and Detection of Colorectal Polyps Using Local Polynomial Approximation

  • Filipe Condessa
  • José Bioucas-Dias
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7325)


In this paper we introduce a new methodology to segment and detect colorectal polyps in endoscopic images obtained by a wireless capsule endoscopic device. The cornerstone of our approach is the fact that polyps are protrusions emerging from colonic walls. Thus, they can be segmented by simple curvature descriptors. Curvature is based on derivatives, thus very sensitive to noise and image artifacts. Furthermore, the acquired images are sampled on a grid which further complicates the computation of derivatives. To cope with these degradation mechanisms, we use use Local Polynomial Approximation, which, simultaneously, denoise the observed images and provides a continuous representation suitable to compute derivatives. On the top of the image segmentation, we built a support vector machine to classify the segmented regions as polyps or non-polyps. The features used in the classifier are selected with a wrapper selection algorithm (greedy forward feature selection algorithm with support vector machines). The proposed segmentation and detection methodology is tested in several scenarios presenting very good results both using the same video sequences as training data and testing data (cross-feature validation) and different video sequences as training and testing data.


polyp segmentation polyp detection local polynomial approximation forward stepwise wrapper subsection selection support vector machines 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adler, D., Gostout, C.: Wireless capsule endoscopy. Hospital Physician 1, 16–22 (2003)Google Scholar
  2. 2.
    Bishop, C.: Pattern Recognition and Machine Learning. Springer (2006)Google Scholar
  3. 3.
    Carmo, M.: Differential Geometry of Curves and Surfaces. Prentice-Hall, Inc., Englewood Cliffs (1976)zbMATHGoogle Scholar
  4. 4.
    Cohen, J.: Comprehensive Atlas of High Resolution Endoscopy and Narrowband Imaging, 1st edn. Wiley-Blackwell (June 2007)Google Scholar
  5. 5.
    Coimbra, M., Dinis-Ribeiro, M.: A review of current computer aided diagnosis systems for polyp detection in virtual colonoscopy. In: Proc. Conf. on Telecommunications (May 1, 2009)Google Scholar
  6. 6.
    Figueiredo, I., Prasath, S., Tsai, Y., Figueiredo, P.: Automatic detection and segmentation of colonic polyps in wireless capsule images (September 2010) (unpublished)Google Scholar
  7. 7.
    Huang, A., Summers, R., Hara, A.: Surface curvature estimation for automatic polyp detection. In: Proc. of SPIE Medical Imaging: Physiology, Function and Structure from Medical Images, vol. 5764, pp. 393–402 (2005)Google Scholar
  8. 8.
    Hughes, G.: On the mean accuracy of statistical pattern recognizers. IEEE Transactions on Information Theory 14, 55–63 (1968)CrossRefGoogle Scholar
  9. 9.
    Katkovnik, V., Egiazarian, K., Astola, J.: Local Approximation Techniques in Signal and Image Processing, 1st edn. SPIE Press (September 2006)Google Scholar
  10. 10.
    Potter, J., Slattery, M., Bostick, R., Gapstur, S.: Colon cancer: a review of the epidemiology. Epidemiologic Reviews 15(2), 499–545 (1993)Google Scholar
  11. 11.
    Rachet, B.: Population-based cancer survival trends in England and Wales up to 2007: an assessment of the NHS cancer plan for England. The Lancet Oncology (2009)Google Scholar
  12. 12.
    Tu, Z., Zhou, X., Barbu, A., Bogoni, L., Comaniciu, D.: Probabilistic 3D polyp detection in CT images: The role of sample alignmentGoogle Scholar
  13. 13.
    Vogelstein, B., Fearon, E., Hamilton, S., Kern, S., Preisinger, A., Leppert, M., Smits, A., Bos, J.: Genetic alterations during colorectal-tumor development. New England Journal of Medicine 319(9), 525–532 (1988)CrossRefGoogle Scholar
  14. 14.
    Wijk, C., Ravesteijn, V., Vos, F., Vliet, L.: Detection and segmentation of colonic polyps on implicit isosurfaces by second principal curvature flow. IEEE Transactions on Medical Imaging (2010)Google Scholar
  15. 15.
    van Wijk, C., Truyen, R., van Gelder, R.E., van Vliet, L.J., Vos, F.M.: On Normalized Convolution to Measure Curvature Features for Automatic Polyp Detection. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004, Part I. LNCS, vol. 3216, pp. 200–208. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  16. 16.
    Zhang, D., Lu, G.: A comparative study on shape retrieval using Fourier descriptors with different shape signatures. Victoria 14(1), 1–9 (2001)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Filipe Condessa
    • 1
  • José Bioucas-Dias
    • 1
  1. 1.Instituto de Telecomunicações - Instituto Superior TécnicoLisboaPortugal

Personalised recommendations