Skip to main content
Springer Nature Link
Log in

Comparison of Several Texture Features for Tumor Detection in CE Images

  • ORIGINAL PAPER
  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

Abstract

Capsule endoscopy (CE) has been widely used as a new technology to diagnose gastrointestinal tract diseases, especially for small intestine. However, the large number of images in each test is a great burden for physicians. As such, computer aided detection (CAD) scheme is needed to relieve the workload of clinicians. In this paper, automatic differentiation of tumor CE image and normal CE image is investigated through comparative textural feature analysis. Four different color textures are studied in this work, i.e., texture spectrum histogram, color wavelet covariance, rotation invariant uniform local binary pattern and curvelet based local binary pattern. With support vector machine being the classifier, the discrimination ability of these four different color textures for tumor detection in CE images is extensively compared in RGB, Lab and HSI color space through ten-fold cross-validation experiments on our CE image data. It is found that HSI color space is the most suitable color space for all these texture based CAD systems. Moreover, the best performance achieved is 83.50% in terms of average accuracy, which is obtained by the scheme based on rotation invariant uniform local binary pattern.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Adeler, D. G., and Gostout, C. J., Wireless capsule endoscopy. Hosp Physician. (5):14–22, 2003.

  2. Bourbakis, N., Detecting abnormal patterns in WCE images, Proc. 5th IEEE Conf. on Bioinformatics and Bioengineering (BIBE’05) pp. 232–238, 2005.

  3. Gallo, G., Granata, E., and Scarpulla, G., Wireless capsule endoscopy video segmentation. International workshop on Medical Measurement and Applications. 236–240, 2009.

  4. Vilarino, F., Spyridonos, P., Pujol, O., Vitia’, J., Radeva, P., Automatic detection of intestinal juices in wireless capsule video endoscopy. Proc. 18th Int. Conf. Pattern Recogn. (4):719–722, 2006.

  5. Li, B., and Max Meng, Q.-H., Computer aided detection of bleeding regions in capsule endoscopy images. IEEE Trans. Biomed. Eng. 56:1032–1039, 2009.

    Article  Google Scholar 

  6. Li, B., and Max Meng, Q.-H., Texture analysis for ulcer detection in capsule endoscopy images. Image Vis. Comput. 27:1336–1342, 2009.

    Article  Google Scholar 

  7. Li, B., and Max Meng, Q.-H., Computer-based detection of bleeding and ulcer in wireless capsule endoscopy images by chromaticity moments. Comput. Biol. Med. 39:141–147, 2009.

    Article  Google Scholar 

  8. Lewis, B. S., Benign and malignant tumors of the small bowel. Capsule Endoscopy, Chapter 16, pp. 183–189, 2008.

  9. Wyszecki, G., and Styles, W. S., Color science: Concepts and methods quantitative data and formulae. Wiley, New York, 1982.

    Google Scholar 

  10. Karkanis, S., Galousi, K., and Maroulis, D., Classification of endoscopic images based on texture spectrum, in Proc. Workshop on Machine Learning in Medical Applications, pp. 63–69, 1999.

  11. Karkanis, S. A., Iakovidis, D. K., Maroulis, D. E., Karras, D. A., and Tzivras, M., Computer-aided tumor detection in endoscopic video using color wavelet features. IEEE Trans. Inf. Technol. Biomed. 7(3):141–152, 2003.

    Article  Google Scholar 

  12. Li, B., A study on computer aided diagnosis for wireless capsule endoscopy images. Ph.D thesis, the Chinese University of Hong Kong, September, 2008.

  13. Lewis, B. S., and Swain, P., Capsule endoscopy in the evaluation of patients with suspected small intestinal bleeding: results of a pilot study. Gastrointest. Endosc. 56:349–353, 2002.

    Article  Google Scholar 

  14. Wang, L., and He, D. C., Texture classification using texture spectrum. Pattern Recognit. 23:905–910, 1990.

    Article  Google Scholar 

  15. Ojala, T., Pietikainen, M., and Harwood, D., A comparative study fsof texture measures with classification based on feature distributions. Pattern Recognit. 29:51–59, 1996.

    Article  Google Scholar 

  16. Ojala, T., Pietikainen, M., and Maenpaa, T., Multi-resolution gray-scale and rotation invariant texture classification with local binary pattern. IEEE Trans. PAMI 24(7):971–987, 2007.

    Article  Google Scholar 

  17. Candes, E. J., Demanet, L., Donoho, D. L., Fast discrete curvelet transforms, Applied and Computational Mathematics. California Institute of Technology, 1–44, 2006.

  18. Vapnik, V., The nature of statistical learning theory. Springer Verlag, New York, 1995.

    MATH  Google Scholar 

  19. Chang, C.-C., Lin, C.-J., LIBSVM: a library for support vector machines, Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm. 2001.

  20. Boulougoura, M., Wadge, E., Intelligent systems for computer-assisted clinical endoscopic images analysis. Proceedings of Second International Conference on Biomedical Engineering, Austria: 405–408, 2004.

Download references

Acknowledgments

This work is supported by the Hong Kong Research Grants Council (RGC) General Research Fund (415709) and Innovation and Technology Support Programme (ITS/430/09) in Hong Kong, both awarded to Max Meng. We would like to show our sincere thanks to James Lau, a professor in Prince of Wales Hospital in Hong Kong, for providing us the CE image data.

Author information

Authors and Affiliations

  1. Shenzhen Institute of Advanced Technology, the Chinese Academy of Sciences, Shenzhen, China

    Bao-Pu Li

  2. Department of Electronic Engineering, the Chinese University of Hong Kong, Shatin N.T., Hong Kong SAR, China

    Bao-Pu Li & Max Qing-Hu Meng

Authors
  1. Bao-Pu Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Max Qing-Hu Meng
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Bao-Pu Li.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Li, BP., Meng, M.QH. Comparison of Several Texture Features for Tumor Detection in CE Images. J Med Syst 36, 2463–2469 (2012). https://doi.org/10.1007/s10916-011-9713-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10916-011-9713-2

Keywords