IPMI 2005: Information Processing in Medical Imaging pp 88-100 | Cite as
From Spatial Regularization to Anatomical Priors in fMRI Analysis
Conference paper
Abstract
In this paper, we study Markov Random Fields as spatial smoothing priors in fMRI detection. Relatively high noise in fMRI images presents a serious challenge for the detection algorithms, creating a need for spatial regularization of the signal. Gaussian smoothing, traditionally employed to boost the signal-to-noise ratio, often removes small activation regions. Recently, the use of Markov priors has been suggested as an alternative regularization approach. In this work, we investigate fast approximate inference algorithms for using MRFs in fMRI detection, propose a novel way to incorporate anatomical information into the detection framework, validate the methods through ROC analysis on simulated data and demonstrate their application in a real fMRI study.
Keywords
General Linear Model Detection Accuracy Anatomical Information Gaussian Smoothing fMRI Signal
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.BrainVoyager software package, http://www.brainvoyager.de
- 2.FMRIB software library, http://www.fmrib.ox.ac.uk/fsl
- 3.Besag, J.: Spatial interaction and statistical analysis of lattice systems. Acad. R. Statistical Soc. Series B 36, 721–741 (1974)MathSciNetGoogle Scholar
- 4.Burock, M.A., Dale, A.M.: Estimation and detection of event-related fmri signals with temporally correlated noise: A statistically efficient and unbiased approach. Human Brain Mapping 11, 249–260 (2000)CrossRefGoogle Scholar
- 5.Cosman, E.R., Fisher, J., Wells, W.M.: Exact MAP activity detection in fMRI using a GLM with an ising spatial. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 703–710. Springer, Heidelberg (2004)CrossRefGoogle Scholar
- 6.Dale, A.M., et al.: Cortical Surface-Based Analysis I: Segmentation and Surface Reconstruction. NeuroImage 9, 179–194 (1999)CrossRefGoogle Scholar
- 7.Descombes, X., Kruggel, F., Von Cramon, D.Y.: fMRI signal restoration using a spatio-temporal Markov random field preserving transitions. NeuroImage 8, 340–349 (1998)CrossRefGoogle Scholar
- 8.Descombes, X., Kruggel, F., Von Cramon, D.Y.: Spatio-temporal fMRI analysis using Markov random fields. IEEE TMI 17(6), 1028–1039 (1998)Google Scholar
- 9.Friston, K.J., et al.: Statistical parametric maps in functional imaging: a general linear approach. Human Brain Mapping 2, 189–210 (1995)CrossRefGoogle Scholar
- 10.Friston, K.J., et al.: Assessing the significance of local activations using their spatial extent. Human Brain Mapping 1, 210–220 (1994)CrossRefGoogle Scholar
- 11.Geman, S., McClure, D.: Statistical methods for tomographic image reconstruction. In: Proc. 46th Session of ISI, vol. 51, pp. 22–26 (1987)Google Scholar
- 12.Geman, S., Reynolds, G.: Constrained restoration and recovery of discontinuities. IEEE Trans. PAMI 14, 367–383 (1992)Google Scholar
- 13.Greig, D.M., Porteous, B.T., Gramon, D.Y.: Exact maximum a posteriori estimation for binary images. J. R. Statistical Society 51, 271–279 (1989)Google Scholar
- 14.Hartvig, N.V.: A stochastic Geometry model for functional Magnetic resonance images. Scandinavian Journal of Statistics 29, 333–353 (2002)MATHCrossRefMathSciNetGoogle Scholar
- 15.Hojen-Sorensen, F., Hansen, L.K., Rasmussen, C.E.: Bayesian modeling of fMRI time series. Adv. Neuroinform. Processing Syst. 12, 754–760 (2000)Google Scholar
- 16.Kapur, T., et al.: Enhanced spatial priors for segmentation of magnetic resonance imagery. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 148–157. Springer, Heidelberg (1998)Google Scholar
- 17.Langan, D.A., et al.: Use of the mean-field approximation in an EM-based approach to unsupervised stochastic model-based image segmentation. In: Proc. ICASSP, vol. 3, pp. 57–60 (1992)Google Scholar
- 18.Parisi, G.: Statistical Field Theory. Addison-Wesley, Reading (1998)Google Scholar
- 19.Pohl, K.M., et al.: Anatomical guided segmentation with non-stationary tissue class distributions in an expectation-maximization framework. Proc. IEEE ISBI, 81–84 (2004)Google Scholar
- 20.Pohl, K.M., et al.: Incorporating non-rigid registration into expectation maximization algorithm to segment MR images. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2488, pp. 508–515. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 21.Rajapakse, J.C., Piyaratna, J.: Bayesian modeling of fMRI time series. IEEE Transactions on Biomedical Engineering 48, 1186–1194 (2001)CrossRefGoogle Scholar
- 22.Salli, E., et al.: Contextual clustering for analysis of functional MRI data. IEEE TMI 20, 403–413 (2001)Google Scholar
- 23.Wei, X., et al.: Functional MRI of auditory verbal working memory: long-term reproducibility analysis. NeuroImage 21, 1000–1008 (2004)CrossRefGoogle Scholar
- 24.Woolrich, M.W., et al.: Fully Bayesian spatio-temporal modeling of fMRI data. IEEE TMI 23(2), 213–231 (2004)Google Scholar
- 25.Zhang, J.: The mean-field theory in EM procedures for markov random field. IEEE Trans. on Signal Processing 40, 2570–2583 (1992)MATHCrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2005