Segmentation and Detection of Colorectal Polyps Using Local Polynomial Approximation
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.
Keywordspolyp segmentation polyp detection local polynomial approximation forward stepwise wrapper subsection selection support vector machines
Unable to display preview. Download preview PDF.
- 1.Adler, D., Gostout, C.: Wireless capsule endoscopy. Hospital Physician 1, 16–22 (2003)Google Scholar
- 2.Bishop, C.: Pattern Recognition and Machine Learning. Springer (2006)Google Scholar
- 4.Cohen, J.: Comprehensive Atlas of High Resolution Endoscopy and Narrowband Imaging, 1st edn. Wiley-Blackwell (June 2007)Google Scholar
- 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.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Y., Figueiredo, P.: Automatic detection and segmentation of colonic polyps in wireless capsule images (September 2010) (unpublished)Google Scholar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.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
- 9.Katkovnik, V., Egiazarian, K., Astola, J.: Local Approximation Techniques in Signal and Image Processing, 1st edn. SPIE Press (September 2006)Google Scholar
- 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.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.Tu, Z., Zhou, X., Barbu, A., Bogoni, L., Comaniciu, D.: Probabilistic 3D polyp detection in CT images: The role of sample alignmentGoogle Scholar
- 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.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