Abstract
Liver segmentation is an important task in the development of computer-aided multi-phase CT diagnosis system of liver. This paper presents a new approach for segmenting liver from multi-phase abdominal CT images using ICA mixture analysis. In particular, we use the variational Bayesian mixture of ICA method [1] to analyze three-dimensional four-phase abdominal CT images. The analysis results show that the CT images could be divided into a set of clinically and anatomically meaningful components. As to our concern, the organs that surround the liver and have similar intensities, such as stomach, kidney, are nearly completely separated from the liver, which makes the segmentation become much easier than on the original CT images.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Choudrey, R.A., Roberts, S.J.: Variational mixture of Bayesian independent component analyzers. Neural Computation 15(1) (January 2003)
Lee, T.W., Lewicki, M.S.: Upsupervised image classification, segmentation, and enhancement using ICA mixture models. IEEE Trans. on Image Processing 11(3), 270–279 (2002)
Lee, T.W., Lewicki, M.S., Sejnowski, T.J.: ICA mixture models for unsupervised classification and automatic context switching. In: Proceeding of International workshop on Independent Component Analysis, pp. 209–214 (1999)
Hu, X.-B., Shimizu, A., Kobatake, H., et al.: Independent component analysis of four-phase abdominal CT images. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 916–924. Springer, Heidelberg (2004) (to appear)
Lee, T.W., Girolami, M., Sejnowski, T.J.: Independent component analysis using an extended infomax algorithm for mixed sub-Gaussian and super-Gaussian sources. Neural Computation, 11(2), 409–433 (1999)
Attias H: Learning parameters and structure of latent variable models by variational Bayes. Electronic Proceedings of the Fifteenth Annual Conference on Uncertainty in Artificial Intelligence (UAI 1999), http://www2.sis.pitt.edu/~dsl/UAI/uai.html
Hitosugi, T., Shimizu, A., Tamura, M., et al.: Development of a liver extraction method using a level set method and its performance evaluation. Journal of Computer Aided Diagnosis of Medical Images 7(4-2) (June 2003) (in Japanese)
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
Hu, X., Shimizu, A., Kobatake, H., Nawano, S. (2004). Applying ICA Mixture Analysis for Segmenting Liver from Multi-phase Abdominal CT Images. In: Yang, GZ., Jiang, TZ. (eds) Medical Imaging and Augmented Reality. MIAR 2004. Lecture Notes in Computer Science, vol 3150. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28626-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-28626-4_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22877-6
Online ISBN: 978-3-540-28626-4
eBook Packages: Springer Book Archive