Bi-dimensional Statistical Empirical Mode Decomposition-Based Video Analysis for Detecting Colon Polyps Using Composite Similarity Measure
The third leading cause of all deaths from cancer is colorectal cancer (10 % of the total for men and 9.2 % of the total in case of women) (Globocan in Cancer Incidence and Morality Worldwide (2008) . The only prevention is to detect and remove the cancerous adenomatous polyps during optical colonoscopy (OC). This paper proposes bi-dimensional statistical empirical mode decomposition (BSEMD)-based colon polyp detection strategy, wherein a composite similarity measure (CSM) has been used. In this work, separate sets of training and testing samples are opted. Only few samples are randomly chosen for training database, remaining samples make the testing database. The proposed method is implemented on sequences of sample images from an OC video database (Park et al in IEEE Trans. Biomed. Eng 59:1408–1418)  provided by American College of Gastroenterology (American College of Gastroenterology, http://gi.org/) . PCA-based feature extraction is used in this work, as it reduces the dimensions efficiently from the main object. The obtained results demonstrate the achieved improvement in the recognition rates, in comparison with other detection procedures.
KeywordsBi-dimensional statistical empirical mode decomposition (BSEMD) Composite similarity measure (CSM) Colon polyps (CP) Optical colonoscopy (OC)
The work is supported by University Grants Commission, India (UGC) under the University with Potential for Excellence (UPE), phase II scheme awarded to Jadavpur University, Kolkata, India.
- 1.Globocan: Cancer Incidence and Morality Worldwide, (2008) http://www.iarc.fr/en/media-centre/iarcnews/2010/globocan2008.php
- 3.American College of Gastroenterology, http://gi.org/
- 5.Medical Supplies & Equipment Co., http://www.medical-supplies-equipment-company.com/
- 7.Arfia, F.B.,Sabri, A., Messaoud, M.B., Abid, M.: The bidimensional empirical mode decomposition with 2D-DWT for gaussian image denoising. In: Proceedings of 17th International Conference on Digital Signal Processing, pp. 1–5. Corfu (2011)Google Scholar
- 8.Pan, J., Zhang, D., Tang, Y.: A Fractal-based BEMD method for image texture analysis. In: IEEE International Conference on Systems Man and Cybernetics (SMC), pp. 3817–3820. Istanbul (2010)Google Scholar
- 13.Jolliffe I.T.: Principal component analysis. Series: Springer Series in Statistics, 2nd edn., pp. 487. Springer, New York (2002)Google Scholar
- 14.Goshtasby, A.A.: Similarity and dissimilarity measures. Image Registration Principles, Tools and Methods, pp. 7–66. Springer London (2012)Google Scholar
- 15.Maroulis, D.E., Iakovidis, D.K., Karkanis, S.A., Karras, D.A.: CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames. Comput. Methods Programs Biomed, vol. 70, (2), pp. 151–166. Springer-Verlog (2003)Google Scholar
- 19.Linderhed, A.: 2D empirical mode decompositions-in the spirit of image compression. In: Proceedings SPIE 4738, Wavelet and Independent Component Analysis applications IX, vol. 4738, pp. 1–8 (2002)Google Scholar