Profile Scale-Spaces for Multiscale Image Match

We present a novel statistical image-match model for use in Bayesian segmentation, a multiscale extension of image profile models akin to those in Active Shape Models. A spherical-harmonic based 3D shape representation provides a mapping of the object boundary to the sphere S 2, and a scale-space for profiles on the sphere defines a scale-space on the object. A key feature is that profiles are not blurred across the object boundary, but only along the boundary. This profile scale-space is sampled in a coarse-to-fine fashion to produce features for the statistical image-match model. A framework for model-building and segmentation has been built, and testing and validation are in progress with a dataset of 70 segmented images of the caudate nucleus.

[1]  Benjamin B. Kimia,et al.  Volumetric Segmentation of Medical Images by Three-Dimensional Bubbles , 1997, Comput. Vis. Image Underst..

[2]  W. Eric L. Grimson,et al.  Coupled Multi-shape Model and Mutual Information for Medical Image Segmentation , 2003, IPMI.

[3]  Timothy F. Cootes,et al.  The Use of Active Shape Models for Locating Structures in Medical Images , 1993, IPMI.

[4]  Tai Sing Lee,et al.  Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[5]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[6]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[7]  O. Faugeras,et al.  Level set based segmentation with intensity and curvature priors , 2000, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737).

[8]  Anil K. Jain,et al.  Learning-based object detection in cardiac MR images , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  B. Kimia,et al.  Volumetric segmentation of medical images by three-dimensional bubbles , 1995, Proceedings of the Workshop on Physics-Based Modeling in Computer Vision.

[10]  Alan L. Yuille,et al.  Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[12]  John R. Kender,et al.  Sectored Snakes: Evaluating Learned-Energy Segmentations , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Timothy F. Cootes,et al.  Active Shape Models: Evaluation of a Multi-Resolution Method for Improving Image Search , 1994, BMVC.

[14]  Max A. Viergever,et al.  The Gaussian scale-space paradigm and the multiscale local jet , 1996, International Journal of Computer Vision.

[15]  Martin Styner,et al.  Evaluation of 3D Correspondence Methods for Model Building , 2003, IPMI.

[16]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[17]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Guido Gerig,et al.  Elastic model-based segmentation of 3-D neuroradiological data sets , 1999, IEEE Transactions on Medical Imaging.

[19]  Alejandro F Frangi,et al.  A non-linear gray-level appearance model improves active shape model segmentation , 2001, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001).