Abstract
Cone-beam computed tomography (CBCT) can provide true 3D information of anatomical structures, with advantages of much thinner slice thickness and significantly lowered effective dose of radiation. However, CBCT images are extremely low contract and noisy. It is very difficult to segment thin bones. It usually takes 4-5 hours to manually segment a set of CBCT data. To this end, we developed a novel approach based on the joint optimization of alignment and statistical surface representation with wavelet transform for segmentation of CBCT images. It included two main steps: customized wavelet base initialization (CWBI) and base invariant wavelet active shape model (BIWASM). We validated our approach with others by comparing the surface deviation between segmented shape to the ground truth. The results showed that our approach outperformed the others in accuracy and computing time.
Chapter PDF
References
Bertram, M., Duchaineau, M.A., Hamann, B., Joy, K.I.: Generalized B-spline subdivision-surface wavelets for geometry compression. IEEE Transactions on Visualization and Computer Graphics 10(3), 326–338 (2004)
de Bruijne, M., van Ginneken, B., Viergever, M.A., Niessen, W.J.: Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. In: Taylor, C.J., Noble, J.A. (eds.) IPMI 2003. LNCS, vol. 2732, pp. 136–147. Springer, Heidelberg (2003)
Catmull, E., Clark, J.: Recursively generated B-spline surfaces on arbitrary topological meshes. Computer-Aided Design 10, 350–355 (1978)
Cootes, T., Taylor, C.J., Cooper, D.H., Graham, J.: Active Shape Models-Their Training and Application. Computer Vision and Image Understanding 61(1), 38–59 (1995)
Essafi, S., Langs, G., Deux, J.F., Rahmouni, A., Bassez, G., Paragios, N.: Wavelet-driven knowledge-based MRI calf muscle segmentation. In: 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 225–228 (June 2009)
Essafi, S., Langs, G., Paragios, N.: Left Ventricle Segmentation Using Diffusion Wavelets and Boosting. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part II. LNCS, vol. 5762, pp. 919–926. Springer, Heidelberg (2009)
Goodall, C.: Procrustes Methods in the Statistical Analysis of Shape. Journal of the Royal Statistical Society 53(2), 285–339 (1991)
Hormann, K., Lévy, B., Sheffer, A.: Siggraph Course Notes Mesh Parameterization: Theory and Practice. In: SIGGRAPH 2007 Course Notes, pp. 1–122. ACM, New York (2007)
Naitoh, M., Hirukawa, A., Katsumata, A., Ariji, E.: Evaluation of voxel values in mandibular cancellous bone: relationship between cone-beam computed tomography and multislice helical computed tomography. Clin. Oral Implants Res. (2009)
Scarfe, W.C., Farman, A.G., Sukovic, P.: Clinical applications of cone-beam computed tomography in dental practice. J. Can. Dent. Assoc. 72(1), 75–80 (2006)
White, S.C., Pharoah, M.J.: Oral Radiology: Principles and Interpretation, 4th edn. Mosby, St. Louis (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chang, YB. et al. (2013). A Novel Approach Based on Joint Optimization of Alignment and Statistical Surface Representation with Wavelet Transform for CBCT Segmentation. In: Peterson, L.E., Masulli, F., Russo, G. (eds) Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2012. Lecture Notes in Computer Science(), vol 7845. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38342-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-38342-7_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38341-0
Online ISBN: 978-3-642-38342-7
eBook Packages: Computer ScienceComputer Science (R0)