Abstract
Modern datasets are often multiway in nature and can contain patterns common to a mode of the data (e.g. space, time, and subjects). Multiway decomposition such as parallel factor analysis (PARAFAC) take into account the intrinsic structure of the data, and sparse versions of these methods improve interpretability of the results. Here we propose a variational Bayesian parallel factor analysis (VB-PARAFAC) model and an extension with sparse priors (SP-PARAFAC). Notably, our formulation admits time and subject specific noise modeling as well as subject specific offsets (i.e., mean values). We confirmed the validity of the models through simulation and performed exploratory analysis of positron emission tomography (PET) and functional magnetic resonance imaging (fMRI) data. Although more constrained, the proposed models performed similarly to more flexible models in approximating the PET data, which supports its robustness against noise. For fMRI, both models correctly identified task-related components, but were not able to segregate overlapping activations.
J.L. Hinrich and M. Mørup were supported by the Lundbeck Foundation (grant. no. R105-9813).
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
References
Jolliffe, I.: Principal Component Analysis, vol. 487. Springer, New York (1986)
Tipping, M., Bishop, C.: Probabilistic principal component analysis. Royal Stat. Soc. 23(3), 492–503 (1999)
Guan, Y., Dy, J.: Sparse probabilistic principal component analysis. In: International Conference on Artificial Intelligence and Statistics, pp. 185–192 (2009)
Harshman, R.: Foundations of the parafac procedure: models and conditions for an “explanatory” multi-modal factor analysis. (1970)
Carroll, J., Chang, J.: Analysis of individual differences in multidimensional scaling via an n-way generalization of eckart-young decomposition. Psychometrika 35(3), 283–319 (1970)
Hitchcock, F.: The expression of a tensor or a polyadic as a sum of products. J. Math. Phys. 6(1), 164–189 (1927)
Kruskal, J.: Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics. Linear Algebra Appl. 18(2), 95–138 (1977)
Kolda, T., Bader, B.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Acar, E., Yener, B.: Unsupervised multiway data analysis: a literature survey. IEEE Trans. Knowl. Data Eng. 21(1), 6–20 (2009)
Mørup, M.: Applications of tensor (multiway array) factorizations and decompositions in data mining. Wiley Interdisc. Rev. Data Mining Knowl. Disc. 1(1), 24–40 (2011)
Rasmussen, M., Bro, R.: A tutorial on the lasso approach to sparse modeling. Chemometr. Intell. Lab. Syst. 119, 21–31 (2012)
Attias, H.: A variational bayesian framework for graphical models. Adv. Neural Inform. Process. Syst. 12(1–2), 209–215 (2000)
Nielsen, F.: Variational approach to factor analysis and related models (2004)
Ermis, B., Cemgil, A.: A Bayesian tensor factorization model via variational inference for link prediction 3, 1–9. arXiv preprint arXiv:1409.8276 (2014)
Zhao, Q., Zhang, L., Cichocki, A., Hoff, P.: Bayesian CP factorization of incomplete tensors with automatic rank determination 37(9), 1–15. arXiv preprint arXiv:1401.6497v2 (2015)
Guo, W., Yu, W.: Variational Bayesian PARAFAC decomposition for Multidimensional Harmonic Retrieval. In: Proceedings of 2011 IEEE CIE International Conference on Radar, RADAR 2011, vol. 2, pp. 1864–1867 (2011)
Bishop, C.: Variational principal components. In: Ninth International Conference on Artificial Neural Networks, ICANN 1999 (Conf. Publ. No. 470), vol. 1, pp. 509–514. IET (1999)
Robert, P., Escoufier, Y.: A unifying tool for linear multivariate statistical methods: the RV-coefficient. Appl. Stat. 25, 257–265 (1976)
Andersson, C.A., Bro, R.: The N-way toolbox for MATLAB. Chemometr. Intell. Lab. Syst. 52(1), 1–4 (2000)
Andersson, J., Jenkinson, M., Smith, S.: Non-linear registration aka Spatial normalisation. FMRIB Technial report TR07JA2, p. 22, June 2007
Knudsen, G., Jensen, P., Erritzoe, D., Baaré, W., Ettrup, A., Fisher, P., Gillings, N., Hansen, H., Hansen, L., Hasselbalch, S., Henningsson, S., Herth, M., Holst, K., Iversen, P., Kessing, L., Macoveanu, J., Madsen, K., Mortensen, E., Nielsen, F., Paulson, O., Siebner, H., Stenbæk, D., Svarer, C., Jernigan, T., Strother, S., Frokjaer, V.: The center for integrated molecular brain imaging (Cimbi) database. NeuroImage 124, 1213–1219 (2015)
Fischl, B.: FreeSurfer. Neuroimage 62(2), 774–781 (2012)
Greve, D., Fischl, B.: Accurate and robust brain image alignment using boundary-based registration. Neuroimage 48(1), 63–72 (2009)
Calhoun, V., Liu, J., Adali, T.: A review of group ICA for fMRI data and ICA for joint inference of imaging, genetic, and ERP data. NeuroImage 45(1 Suppl), S163–S172 (2009)
Beckmann, C., Smith, S.: Tensorial extensions of independent component analysis for multisubject FMRI analysis. NeuroImage 25(1), 294–311 (2005)
Jenkinson, M., Bannister, P., Brady, M., Smith, S.: Improved optimization for the robust and accurate linear registration and motion correction of brain images. NeuroImage 17(2), 825–841 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Beliveau, V., Papoutsakis, G., Hinrich, J.L., Mørup, M. (2017). Sparse Probabilistic Parallel Factor Analysis for the Modeling of PET and Task-fMRI Data. In: Müller, H., et al. Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging. BAMBI MCV 2016 2016. Lecture Notes in Computer Science(), vol 10081. Springer, Cham. https://doi.org/10.1007/978-3-319-61188-4_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-61188-4_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61187-7
Online ISBN: 978-3-319-61188-4
eBook Packages: Computer ScienceComputer Science (R0)