Evaluation and Comparison of Textural Feature Representation for the Detection of Early Stage Cancer in Endoscopy

Arnaud A. A. Setio, Fons van der Sommen, Svitlana Zinger, Erik J. Schoon, Peter H. N. de With

Abstract

Esophageal cancer is the fastest rising type of cancer in the Western world. The novel technology of High Definition (HD) endoscopy enables physicians to find texture patterns related to early cancer. It encourages the development of a Computer-Aided Decision (CAD) system in order to help physicians with faster identification of early cancer and decrease the miss rate. However, an appropriate texture feature extraction, which is needed for classification, has not been studied yet. In this paper, we compare several techniques for texture feature extraction, including co-occurrence matrix features, LBP and Gabor features and evaluate their performance in detecting early stage cancer in HD endoscopic images. In order to exploit more image characteristics, we introduce an efficient combination of the texture and color features. Furthermore, we add a specific preprocessing step designed for endoscopy images, which improves the classification accuracy. After reducing the feature dimensionality using Principal Component Analysis (PCA), we classify selected features with a Support Vector Machine (SVM). The experimental results validated by an expert gastroenterologist show that the proposed feature extraction is promising and reaches a classification accuracy up to 96.48%.

References

  1. Chang, C.-C. and Lin, C.-J. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1-27:27.
  2. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20:273-297.
  3. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, pages 886 -893 vol. 1.
  4. Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural Features for Image Classification. Systems, Man and Cybernetics, IEEE Transactions on, 3(6):610 - 621.
  5. Howlader, N., Noone, A., Krapcho, M., Neyman, N., Aminou, R., Altekruse, S., Kosary, C., Ruhl, J., Tatalovich, Z., Cho, H., Mariotto, A., Eisner, M., Lewis, D., Chen, H., EJ, F., and Cronin, K. (2012). Seer cancer statistics review.
  6. Kang, J. and Doraiswami, R. (2003). Real-time image processing system for endoscopic applications. In Electrical and Computer Engineering, 2003. IEEE CCECE 2003. Canadian Conference on, volume 3.
  7. Kara, M. A., Curvers, W. L., and Bergman, J. J. (2010). Advanced Endoscopic Imaging in Barrett's Esophagus. Techniques in Gastrointestinal Endoscopy, 12(2):82- 89.
  8. Khellah, F. (2011). Texture classification using dominant neighborhood structure. Image Processing, IEEE Transactions on, 20(11):3270 -3279.
  9. Lahajnar, F. and Kovacic, S. (2003). Rotation-invariant texture classification. Pattern Recognition Letters, 24.
  10. Liedlgruber, M. and Uhl, A. (2011). Computer-aided decision support systems for endoscopy in the gastrointestinal tract: A review. Biomedical Engineering, IEEE Reviews in, 4:73 -88.
  11. Ng, C., Lu, G., and Zhang, D. (2005). Performance study of gabor filters and rotation invariant gabor filters. In Multimedia Modelling Conference, 2005. MMM 2005. Proceedings of the 11th International.
  12. Ojala, T., Pietikäinen, M., and Maenpaa, T. (2002). Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7):971-987.
  13. Saint-Pierre, C.-A., Boisvert, J., Grimard, G., and Cheriet, F. (2011). Detection and correction of specular reflections for automatic surgical tool segmentation in thoracoscopic images. Mach. Vision Appl., 22(1).
  14. Tchoulack, S., Pierre Langlois, J., and Cheriet, F. (2008). A video stream processor for real-time detection and correction of specular reflections in endoscopic images. In Circuits and Systems and TAISA Conference, 2008. NEWCAS-TAISA 2008. 2008 Joint 6th International IEEE Northeast Workshop on, pages 49 -52.
  15. Unser, M. (1995). Texture classification and segmentation using wavelet frames. Image Processing, IEEE Transactions on, 4(11):1549 -1560.
  16. Vecsei, A., Fuhrmann, T., and Uhl, A. (2008). Towards automated diagnosis of celiac disease by computerassisted classification of duodenal imagery. In Advances in Medical, Signal and Information Processing, 2008. 4th IET International Conference on.
  17. Vilarino, F., Spyridonos, P., Pujol, O., Vitria, J., and Radeva, P. (2006). Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy. In Pattern Recognition (ICPR'06), 18th International Conference on, pages 719-722, Hong Kong. IEEE.
  18. Wang, L. and He, D.-C. (1990). Texture Classification using Texture Spectrum. Pattern Recognition, 23(8).
  19. Zhang, G. and Ma, Z.-M. (2007). Texture feature extraction and description using gabor wavelet in content-based medical image retrieval. In Wavelet Analysis and Pattern Recognition, 2007. International Conference on, volume 1, pages 169 -173.
Download


Paper Citation


in Harvard Style

A. A. Setio A., van der Sommen F., Zinger S., Schoon E. and de With P. (2013). Evaluation and Comparison of Textural Feature Representation for the Detection of Early Stage Cancer in Endoscopy . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 238-243. DOI: 10.5220/0004204502380243


in Bibtex Style

@conference{visapp13,
author={Arnaud A. A. Setio and Fons van der Sommen and Svitlana Zinger and Erik J. Schoon and Peter H. N. de With},
title={Evaluation and Comparison of Textural Feature Representation for the Detection of Early Stage Cancer in Endoscopy},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={238-243},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004204502380243},
isbn={978-989-8565-47-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Evaluation and Comparison of Textural Feature Representation for the Detection of Early Stage Cancer in Endoscopy
SN - 978-989-8565-47-1
AU - A. A. Setio A.
AU - van der Sommen F.
AU - Zinger S.
AU - Schoon E.
AU - de With P.
PY - 2013
SP - 238
EP - 243
DO - 10.5220/0004204502380243