Toward Consistently Behaving Deformable Models For Improved Automation In Image Segmentation
Deformable models are a powerful approach to medical image segmentation. However, currently the behavior of a deformable model is highly dependent on its initialization and parameter settings. This is an obstacle to robust automatic or near-automatic segmentation. A generic approach to reducing this dependency is introduced in the present chapter based on topographic distance transforms from manually or automatically placed markers. This approach utilizes object and background differentiation through watershed theories. The implementation is based on efficient numerical methods such as the Fast Marching method and non-iterative reconstruction-by-erosion. Further extension into a multi-region coupled segmentation approach is discussed. Validation experiments are presented to demonstrate the capabilities of this approach. A preliminary application in pediatric dosimetry research is described. It is believed that the more consistent behavior will enable a higher degree of automation for segmentation employing deformable models and is particularly suited for applications that involve segmentation-based construction of organ models from image databases, especially in situations where the markers can be placed automatically based on a priori knowledge.
KeywordsManual Segmentation Deformable Model Geodesic Active Contour Fast Marching Method Background Marker
Unable to display preview. Download preview PDF.
- 6.Cootes T, Taylor C. 2001. Statistical models of appearance for medical image analysis and com-puter vision. In Proc SPIE Med Imaging 4322:236-248.Google Scholar
- 11.Ho S, Bullitt E, Gerig G. 2002. Level set evolution with region competition: automatic 3D segmentation of brain tumors. In R. Kasturi, D. Laurendeau, and C. Suen, editors, Proceedings of the 16th international conference on pattern recognition, pp. 532-535. Washington, DC: IEEE Computer Society.Google Scholar
- 14.Chen T, Metaxas D. 2002. Integration of Gibbs prior models and deformable models for 3D medical image segmentation. In Proceedings of the 16th international conference on pattern recognition, Vol. 1, pp. 719-722. Washington, DC: IEEE Computer Society.Google Scholar
- 15.Metaxas D, Chen T. 2004. A hybrid 3D segmentation framework. IEEE Int Symp Biomed Imaging 1:13-16.Google Scholar
- 24.Maragos P, Butt MA. 1998. Advances in differential morphology: image segmentation via eikonal PDE and curve evolution and reconstruction via constrained dilation flow. In Mathematical mor-phology and its applications to image and signal processing, pp. 167-174. Ed HJAM Heijmans, JBTM Roerdink. Amsterdam: Kluwer Academic.Google Scholar
- 27.Meyer F, Maragos P. 1999. Multiscale morphological segmentations based on watershed, flood-ing, and eikonal PDE. Scale-space theories in computer vision, pp. 351-362. Ed M Nielsen, P Johansen, OF Olsen, J Weickert. Berlin: Springer.Google Scholar
- 31.Maragos P, Butt MA, Pessoa LFC. 1998. Two frontiers in morphological image analysis: dif-ferential evolution models and hybrid morphological/linear neural networks. In Proceedings of the international symposium on computer graphics, image processing and vision, Vol. 11, pp. 10-17. http://cvsp.cs.ntua.gr/publications/confr/MaragosButtPesoa DifMorfMRLNN SIB-GRAPI1998.pdf.
- 37.Marr D, Hildreth E. 1980. Theory of edge detection. Proc Roy Soc London B207:187-217.Google Scholar
- 38.Lorigo LM, Faugeras OD, Grimson WEL, Keriven R, Kikinis R, and Westin C-F. 1999. Co-dimension 2 geodesic active contours for MRA segmentation. In Proceedings of the international conference on information processing in medical imaging, pp. 126-133. Washington, DC: IEEE Computer Society.CrossRefGoogle Scholar
- 40.Yushkevich PA, Piven J, Cody H, Ho S, Gee JC, Gerig G. 2005. User-guided level set segmentation of anatomical structures with ITK-SNAP. Insight J. To appear.Google Scholar
- 41.Kaus M, Warfield SK, Nabavi A, Jolesz FA, Black PM, Kikinis R. 2001. Automated segmentation of MRI of brain tumors. Radiology 218(2):586-591.Google Scholar
- 42.Brenner DJ, Elliston CD, Hall EJ. 2001. Estimated risks of radiation-induced fatal cancer from pediatric CT. Am J Roentgenol 176:289-296.Google Scholar
- 43.Curry TS, Dowdey JE, Murry RC. 1990. Christensen’s physics of diagnostic radiology. Philadel- phia: Lea & Febiger.Google Scholar
- 44.McLean D, Barclay L, Li R, Ourselin S. 2006. Estimation of paediatric tissue characteristics from CT image analysis. In Proceeding of the 6th international topical meeting on industrial radiation and radioisotope measurement applications. Lecture notes in computer science, Vol. 3708. Ed J Blanc-Talon, W Philips, DC Popescu, P Scheunders. Berlin: Springer. To appear.Google Scholar
- 46.Paragios N, Deriche R. 2000. Coupled geodesic active regions for image segmentation: a level set approach. In Proceedings of the sixth European conference on computer vision, Part 2. Lecture notes in computer science, Vol. 1843, pp. 224-240. Berlin: Springer.Google Scholar