Abstract
This paper presents a novel algorithm for prostate tissue characterization based on Trans-rectal Ultrasound (TRUS) images. A Gabor multi-resolution technique is designed to automatically identify the Regions of Interest (ROI) in the segmented prostate image. These ROIs are the high probable cancerous regions in the gland. Furthermore, statistical texture analysis for these regions is carried out by employing Grey Level Difference Matrix (GLDM), where a set of features is constructed. The next stage is mainly feature selection that defines the most salient subset of the constructed features using exhaustive search. The selected feature set is found to be useful for the discrimination between cancerous and non-cancerous tissues. Least Square Support Vector Machines (LS-SVM) classifier is then applied to the selected feature set for the purpose of tissue characterization. The obtained results demonstrate excellent tissue characterization.
Chapter PDF
References
Shen, D., Zhan, Y., Davatzikos, C.: Segmentation of prostate boundaries from ultrasound images using statistical shape model. IEEE Transactions on Medical Imaging 22(4), 539–551 (2003)
Gong, L., Pathak, S.D., Haynor, D.R., Cho, P.S., Kim, Y.: Parametric shape modeling using deformable superellipses for prostate segmentation. IEEE Transactions on Medical Imaging 23(3), 340–349 (2004)
Clausi, D.A., Jernigan, M.E.: Designing Gabor filters for optimal texture separability. Pattern Recognition 33, 1835–1849 (2000)
Bovik, A.C., Clark, M., Geisler, W.S.: Multichannel texture analysis using localized spatial filters. IEEE Trans. Pattern Anal. Machine Intell. 12(1), 55–73 (1990)
Mohamed, S.S., El-Saadany, E.F., Abdel-Galil, T.K., Shen, J., Salama, M.M., Fenster, A., Downey, D.B., Rizkalla, K.: Region of Interest Identification in TRUS Images of the Prostate Based on Gabor Filter. In: IEEE Midwest Symposium on circuits and systems (2003)
Bhanu Prakash, K.N., Ramakrishnan, A.G., Suresh, S., Chow, T.W.P.: Fetal lung maturity analysis using ultrasound image features. IEEE Transactions on Information Technology in Biomedicine 6(1), 38–45 (2002)
Duda, R., Hart, P., Stork, D.: Pattern Classification. John Wiley and Sons, Chichester (2001)
Junli, C., Licheng, J.: Classification mechanisms for SVM. In: Proceedings of ICSP 2000(2000)
Suykens, J.A.K., Vandewalle, J.: Least Squares Support Vector Machine classifiers. Neural Processing Letters 9(3), 293–300 (1999)
Pelckmans, K., Suykens, J.A.K., Van Gestel, T., De Brabanter, J., Lukas, L., Hamers, B., De Moor, B., Vandewalle, J.: LS-SVMlab Toolbox User’s Guide. Pattern recognition letters 24, 659–675 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mohamed, S.S., Salama, M.M.A., Kamel, M., Rizkalla, K. (2004). Region of Interest Based Prostate Tissue Characterization Using Least Square Support Vector Machine LS-SVM. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2004. Lecture Notes in Computer Science, vol 3212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30126-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-30126-4_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23240-7
Online ISBN: 978-3-540-30126-4
eBook Packages: Springer Book Archive