This Article 
 Bibliographic References 
 Add to: 
Sectored Snakes: Evaluating Learned-Energy Segmentations
September 2001 (vol. 23 no. 9)
pp. 1028-1034

—We describe how to teach deformable models to maximize image segmentation correctness based on user-specified criteria, and we present a method for evaluating which criteria work best. A traditional deformable model (“snake” in 2D) fails to find an object's boundary when the strongest nearby image edges are not the ones sought. But models can be trained to respond to other image features instead, by learning their probability distributions. The implementor must then decide on which of many image qualities to teach the model. To this end, we show how to evaluate the efficacy of any resulting deformable model, given a sampling of ground truth, a model of the range of shapes tried during optimization, and a measure of shape closeness. In the domain of abdominal CT images, we demonstrate such evaluation on a simple “sectoring” of a snake in which intensity and perpendicular gradient are observed over equal-length segments. This specific set of qualities shows a measured improvement over an objective function that is uniform around the shape, and it follows naturally from examination of the latter's failures due to image variations around the organ boundary.

[1] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. IEEE Int'l Conf. Computer Vision, pp. 259-268, 1987.
[2] T.E. Boult, S.D. Fenster, and T. O'Donnell, “Reinterpreting Physically-Motivated Modeling,” Proc. ARPA Image Understanding Workshop, Nov. 1994.
[3] K.F. Lai and R.T. Chin, "Deformable Contours—Modeling and Extraction," Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 11, pp. 1,084-1,090, 1995.
[4] T.F. Cootes, C.J. Taylor, A. Lanitis, D.H. Cooper, and J. Graham, "Building and Using Flexible Models Incorporating Grey-Level Information," Proc. Fourth Int'l Conf. Computer Vision, pp. 242-246.Los Alamitos, Calif.: IEEE CS Press, 1993.
[5] B. Baldwin, “Multiscale Snakes,” PhD thesis, Courant Inst. of New York Univ., 1997.
[6] C.A. Davatzikos and J.L. Prince, “An Active Contour Model for Mapping the Cortex,” IEEE Tran. Medical Imaging, vol. 14, pp. 65-80, Mar. 1995
[7] S.D. Fenster and J.R. Kender, “Sectored Snakes: Evaluating Learned-Energy Segmentations,” Proc. IEEE Int'l Conf. Computer Vision, pp. 420-426, Jan. 1998.
[8] R.P. Grzeszczuk and D.N. Levin, Brownian Strings : Segmenting Images with Stochastically Deformable Contours IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, pp. 1100-1114, 1997.
[9] J.L. Boes, C.R. Meyer, and T.E. Weymouth, “Liver Definition in CT Using a Population-Based Shape Model,” Proc. First Int'l Conf. Computer Vision, Virtual Reality, and Robotics in Medicine (CVRMed '95), pp. 506-512, Apr. 1995.
[10] C. Kervrann and F. Heitz, “A Hierarchical Statistical Framework for the Segmentation of Deformable Objects in Image Sequences,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 724-728, June 1994.
[11] V. Ramesh, “Performance Evaluation of Image Understanding Algorithms,” PhD thesis, Univ. of Washington, 1995.
[12] G. Borgefors, "Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, pp. 849-865, 1988.
[13] V. Chalana and Y. Kim, “A Methodology for Evaluation of Boundary Detection Algorithms on Medical Images,” IEEE Trans. Medical Imaging, vol. 16, no. 6, pp. 642-652, 1997.
[14] D.J. Williams and M. Shah, “Edge Contours Using Multiple Scales,” Computer Vision, Graphics, and Image Processing, vol. 51, pp. 256-274, Sept. 1990.

S.D. Fenster, J.R. Kender, "Sectored Snakes: Evaluating Learned-Energy Segmentations," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 9, pp. 1028-1034, Sept. 2001, doi:10.1109/34.955115
Usage of this product signifies your acceptance of the Terms of Use.