Hausdorff Distance Constraint for Multi-surface Segmentation
It is well known that multi-surface segmentation can be cast as a multi-labeling problem. Different segments may belong to the same semantic object which may impose various inter-segment constraints . In medical applications, there are a lot of scenarios where upper bounds on the Hausdorff distances between subsequent surfaces are known. We show that incorporating these priors into multi-surface segmentation is potentially NP-hard. To cope with this problem we develop a submodular-supermodular procedure that converges to a locally optimal solution well-approximating the problem. While we cannot guarantee global optimality, only feasible solutions are considered during the optimization process. Empirically, we get useful solutions for many challenging medical applications including MRI and ultrasound images.
Unable to display preview. Download preview PDF.
- 1.Delong, A., Boykov, Y.: Globally optimal segmentation of multi-region objects. In: IEEE ICCV, Kyoto, Japan, pp. 285–292 (2009)Google Scholar
- 4.Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. In: IEEE Int. Conf. on CVPR, pp. 755–762 (2005)Google Scholar
- 8.Narasimhan, M., Bilmes, J.A.: A submodular-supermodular procedure with applications to discriminative structure learning. In: UAI, pp. 404–412 (2005)Google Scholar
- 10.Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching - incorporating a global constraint into mrfs. In: IEEE Int. Conf. on CVPR, pp. 993–1000 (2006)Google Scholar
- 12.Karzanov, A.V.: Quick algorithm for determining the distance from the points of the given subset of an integer lattice to the points of its complement. Cybernetics and System Analysis, 177–181 (1992); translation by Julia KomissarchikGoogle Scholar
- 13.Felzenszwalb, P., Huttenlocher, D.: Distance transforms of sampled functions. Computing and Information Science TR2004-1963, Cornell (2004)Google Scholar
- 17.Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE PAMI 24, 657–673 (2004)Google Scholar