A user-guided tool for efficient segmentation of medical image data
The lack of robust and reproducible methods for object segmentation still impedes the introduction of image postprocessing as widely used routine tools in clinical environments. In this paper, we present new tools for the segmentation of two- and three-dimensional objects from multidimensional image data. Our strategy is twofold: After creating an extended graph description of contour fragments and a tessellation of the image plane which is a fully automatic process running in the background, a user can choose between an interactive and a model-based segmentation procedure. A contour grouping algorithm based on path optimization can be used when full user interaction is required. Interactivity is limited to a few simple and quick operations. Another, region-based method uses a split- and-merge strategy and discrete optimization with global shape criteria. Grouping of primitive region patches is invoked by a contour model and a comparison of shape features. In combination, the two procedures form an efficient slice-propagation technique for the segmentation of volumetric objects from three-dimensional image data.
Unable to display preview. Download preview PDF.
- 1.J.F. Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.Google Scholar
- 2.Tuomo S. Vehkomäki. Image Segmentation by Contour Grouping: Knowledge Based Search in Attributed Proximity Graph. Ph.d. thesis, Swiss Federal Institute of Technology ETH, 1995. Number 11211.Google Scholar
- 3.R. Ogniewicz and M. Ilg. Voronoi skeletons: Theory and applications. In Proc. of Conf. on Computer Vision and Pattern Recognition, Champaign, Illinois, pages 63–69, June 1992.Google Scholar
- 4.P. Robinson, A.C.F. Colchester, L.D. Griffin, and D.J. Hawkes. Integrated skeleton and boundary shape representation for medical image interpretation. In G. Sandini, editor, Proceedings of European Conference on Computer Vision ECCV'92, volume 588 of LNCS-Series, pages 725–729. Springer-Verlag, 1992.Google Scholar
- 5.Tuomo Vehkomäki, Guido Gerig, and Gabor Székely. Segmentation of volume data by contour fragment grouping. In Proceedings of CAR'95 Computer Assisted Radiology, June 1995.Google Scholar
- 6.Robert Sedgewick. Algorithms. Addison-Wesley, 1983.Google Scholar
- 7.Graig A. Shelley. Heuristic approach for displaying chemical structures. J. Chem. Inf. Comput. Sci., 23(2), 1983.Google Scholar
- 8.J. K. Udupa, S. Samarasekera, and W. A. Barrett. Boundary detection via dynamic programming. In Richard A. Robb, editor, Proc. of Visualization in Biomedical Computing, pages 33–39. SPIE, 1992.Google Scholar
- 9.Glenn Shafer. A Mathematical Theory of Evidence. Princeton University Press, 1976.Google Scholar
- 10.Colin R. Reeves. Modern Heuristic Techniques for Combinatorial Problems. Blackwell Scientific Publications, 1993.Google Scholar
- 11.M. Kuhn et al. COVIRA: Multimodality Medical Image Analysis for Diagnosis and Treatment Planning: COmputer Vision in RAdiology. In M.J. Ladeira M.F. Laires and J.P. Christensen, editors, Studies in Health Technology and Informatics, volume 24, pages 138–160, IOS Press Amsterdam, 1995. see original paper for full list of authors.Google Scholar
- 12.F. Maes, D. Vandermeulen, P. Suetens, and G. Marchal. Computer-aided Interactive Object Delineation Using an Intelligent Patinbrush Technique. In Nicholas Ayache, editor, Proceedings First Int. Conf. CVRMED'95, number 905 in Lecture Notes in Computer Science, pages 77–83. Springer, January 1995.Google Scholar
- 13.L.D. Griffin, A.C.F. Colchester, S.A. Roell, and C.S. Studholm. Hierarchical segmentation satisfying constraints. In E.R. Hancock, editor, Proceedings of British Machine Vision Conference, pages 135–144. Sheffield: BMVA Press, 1995.Google Scholar