A Learning Based Approach for 3D Segmentation and Colon Detagging
Foreground and background segmentation is a typical problem in computer vision and medical imaging. In this paper, we propose a new learning based approach for 3D segmentation, and we show its application on colon detagging. In many problems in vision, both the foreground and the background observe large intra-class variation and inter-class similarity. This makes the task of modeling and segregation of the foreground and the background very hard. The framework presented in this paper has the following key components: (1) We adopt probabilistic boosting tree  for learning discriminative models for the appearance of complex foreground and background. The discriminative model ratio is proved to be a pseudo-likelihood ratio modeling the appearances. (2) Integral volume and a set of 3D Haar filters are used to achieve efficient computation. (3) We devise a 3D topology representation, grid-line, to perform fast boundary evolution. The proposed algorithm has been tested on over 100 volumes of size 500 × 512 × 512 at the speed of 2 ~ 3 minutes per volume. The results obtained are encouraging.
KeywordsGrid Node Discriminative Model Input Volume Virtual Colonoscopy Boundary Evolution
Unable to display preview. Download preview PDF.
- 1.Bennett, K.P., Blue, J.A.: A Support Vector Machine Approach to Decision Trees. In: Proc. of IJCNN (1998)Google Scholar
- 3.Chen, D., Liang, Z., Wax, M., Li, L., Li, B., Kaufman, A.: A Novel Approach to Extract Colon Lumen from CT Images for Virtual Colonoscopy. IEEE Tran. Medical Imaging 19(12) (2000)Google Scholar
- 5.Freund, Y., Schapire, R.: A Decision-theoretic Generalization of On-line Learning And an Application to Boosting. J. of Comp. and Sys. Sci. 55(1) (1997)Google Scholar
- 6.Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting., Dept. of Statistics, Stanford Univ. Technical Report (1998)Google Scholar
- 7.Malandain, G., Bertrand, G., Ayache, N.: Topological Segmentation of Discrete Surfaces. Intl. J. of Computer Vision 10(2) (1993)Google Scholar
- 9.Tu, Z.: Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering. In: Proc. of ICCV (2005)Google Scholar
- 10.Tu, Z.: An Integrated Framework for Image Segmentation and Perceptual Grouping. In: Proc. of ICCV (2005)Google Scholar
- 11.Pizer, S., et al.: Deformable M-Reps for 3D Medical Image Segmentation. Intl. J. of Computer Vision 55(2) (2003)Google Scholar
- 13.Viola, P., Jones, M.: Fast Multi-view Face Detection. In: Proc. of CVPR (2001)Google Scholar
- 14.Yezzi, A., Soatto, S.: Stereoscopic segmentation. Intl. J. of Computer Vision 53(1) (2003)Google Scholar
- 15.Zalis, M.E., Perumpillichira, J., Hahn, P.F.: Digital Subtraction Bowel Cleansing for CT Colonography Using Morphological and Linear Filtration Methods. IEEE Trans. Medical Imaging 23(11) (2004)Google Scholar