Abstract
This paper investigates the segmentation of different regions in PET images based on the feature vector extracted from the timeactivity curve for each voxel. PET image segmentation has applications in PET reference region analysis and activation studies. The segmentation algorithm presented uses a Markov random field model for the voxel class labels. By including the Markov random field model in the expectation-maximisation iteration, the algorithm can be used to simultaneously estimate parameters and segment the image. Hence, the algorithm is able to combine both feature and spatial information for the purpose of segmentation. Experimental results on synthetic and real PET data are presented to demonstrate the performance of the algorithm. The algorithms used in this paper can be used to segment other functional images.
Acknowledgements
The authors wish to thank the Richard Banati and Ralph Myers at the Medical Research CouncilC yclotron Unit for discussions and the provision of data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lammertsma, A.A. and Hume, S.P.: Simplified reference tissue model for PET receptor studies, Neuroimage, 1996, vol. 4, 153–158
Gunn, R.N. and Lammertsma, A.A. and Hume, S.P. and Cunningham, V.J.: Parametric imaging of ligand-receptor binding in PET using a simplified reference region model, Neuroimage, 1997, vol. 6, No.4, 270–287
I.T. Jollife: Principal Component Analysis, New York, Springer-Verlag 1986
H.M. Wu, C.K. Hoh, Y. Choi, H.R. Schelbert, R.A. Hawkins, M.E. Phelps, S.C. Huang: Factor analysis for extraction of blood time-activity curves in dynamic FDG-PET studies, Journal of Nuclear Medicine, 1995, vol. 36, 1714–1722
Ashburner, J., Haslam, J., Taylor, C. and Cunningham, V.J.: A Cluster Analysis Approach for the Characterization of Dynamic PET Data, Quantification of Brain Function Using PET 1996, Academic Press, San Diego, CA. 301–306
Zhengrong Liang, James R. MacFall and Donald P. Harrington: Parameter Estimation and Tissue Segmentation from Multispectral MR Images, IEEE transactions on Medical Imaging, vol. 13, No. 3, September 1994
Geman, S. and Geman, D: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images, IEEE Trans. PAMI, 1984, vol. 6, No. 6, 721–741
Besag, J.E.: On the statistical analysis for dirty pictures, Journal of Royal Statistical Society, 1986, vol. B, No.48, 259–302
Dempster, A.P., Laird, N.M. and Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm, Journal of the Royal Statistical Society 1977, B39(1), 1–38
Jun Zhang, James W. Modestino and David A. Langan: Maximum-likelihood Parameter Estimation for Unsupervised Stochastic Model-Based Image Segmentation, IEEE transactions on image processing, 1994 vol. 3, No.4, 405–419
R.B. Banati, G.W. Goerres and R. Myers: [11C](R)-PK11195 positron emission tomography imaging of activated microglia in vivo in Rasmussen's encephalitis, Neurology, 1999, vol. 53, 2199–2203
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, J.L., Gunn, S.R., Nixon, M.S., Gunn, R.N. (2001). Markov Random Field Models for Segmentation of PET Images. In: Insana, M.F., Leahy, R.M. (eds) Information Processing in Medical Imaging. IPMI 2001. Lecture Notes in Computer Science, vol 2082. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45729-1_50
Download citation
DOI: https://doi.org/10.1007/3-540-45729-1_50
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42245-7
Online ISBN: 978-3-540-45729-9
eBook Packages: Springer Book Archive