Abstract
A novel statistical shape model is presented for automatic and accurate segmentation of prostate boundary from 3D ultrasound (US) images, using a hierarchical texture-based matching method. This method uses three steps. First, Gabor filter banks are used to capture rotation-invariant texture features at different scales and orientations. Second, different levels of texture features are integrated by a kernel support vector machine (KSVM) to optimally differentiate the prostate from surrounding tissues. Third, a statistical shape model is hierarchically deformed to the prostate boundary by robust texture and shape matching. Experimental results test the performance of the proposed method in segmenting 3D US prostate images.
Chapter PDF
Similar content being viewed by others
References
Ghanei, A., Soltanian-Zadeh, H., Ratkesicz, A., Yin, F.: A three-dimensional deformable model for segmentation of human prostate from ultrasound image. Medical Physics 28, 2147–2153 (2001)
Richard, W.D., Keen, C.G.: Automated Texture-based Segmentation of Ultrasound Images of the Prostate. Computerized Medical Imaging and Graphics 20, 131–140 (1996)
Shao, F., Ling, K.V., Ng, W.S.: 3D Prostate Surface Detection from Ultrasound Images Based on Level Set Method. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2489, pp. 389–396. Springer, Heidelberg (2002)
Shen, D., Zhan, Y., Davatzikos, C.: Segmentation Prostate Boundaries from Ultrasound Images Using Statistical Shape Model. IEEE Trans. on Med. Img. 22, 539–551 (2003)
Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2, 121–167 (1998)
Shen, D., Herskovits, E.H., Davatzikos, C.: An adaptive-focus statistical shape model for segmentation and shape modeling of 3D brain structures. IEEE Trans. on Med. Img. 20, 257–270 (2001)
Manjunath, B.S., Ma, W.Y.: Texture Features for Browsing and Retrieval of Image Data. IEEE Trans. on Pattern Anal. Mach. Intell. 18, 837–842 (1996)
Hu, N., Downey, D., Fenster, A., Ladak, H.: Prostate surface segmentation from 3D ultrasound images. In: IEEE International Symposium on Biomedical Imaging, Washington, D. C., pp. 613–616 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhan, Y., Shen, D. (2003). Automated Segmentation of 3D US Prostate Images Using Statistical Texture-Based Matching Method. In: Ellis, R.E., Peters, T.M. (eds) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003. MICCAI 2003. Lecture Notes in Computer Science, vol 2878. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39899-8_84
Download citation
DOI: https://doi.org/10.1007/978-3-540-39899-8_84
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20462-6
Online ISBN: 978-3-540-39899-8
eBook Packages: Springer Book Archive