Ian Davidson
ABSTRACT
We pose the problem of network discovery which involves simplifying spatio-temporal data into cohesive regions (nodes) and relationships between those regions (edges). Such problems naturally exist in fMRI scans of human subjects. These scans consist of activations of thousands of voxels over time with the aim to simplify them into the underlying cognitive network being used. We propose supervised and semi-supervised variations of this problem and postulate a constrained tensor decomposition formulation and a corresponding alternating least squares solver that is easy to implement. We show this formulation works well in controlled experiments where supervision is incomplete, superfluous and noisy and is able to recover the underlying ground truth network. We then show that for real fMRI data our approach can reproduce well known results in neurology regarding the default mode network in resting-state healthy and Alzheimer affected individuals. Finally, we show that the reconstruction error of the decomposition provides a useful measure of the network strength and is useful at predicting key cognitive scores both by itself and with clinical information.
- C.F. Beckmann and S.M. Smith, Tensorial extensions of independent component analysis for multisubject FMRI analysis, NeuroImage 25 (2005) 294--311.Google Scholar
Cross Ref
- M. Barnathan, V. Megalooikonomou, C. Faloutsos, S. Faro, F.B. Mohamed FB, TWave: high-order analysis of functional MRI, Neuroimage. 2011 537--48.Google Scholar
- E. Bullmore and O. Sporns. Complex brain networks: graph theoretical analysis of structural and functional systems. Nat Rev Neurosci, 10(3):186--198, 2009.Google ScholarCross Ref
- J. Burge, T. Lane, H. Link, s. Qiu, and V. Clark, Discrete Dynamic Bayesian Network Analysis of fMRI Data, Human Brain Mapping 30 (2009).Google Scholar
- D. Cordes, V. Haughton, J. D. Carew, K. Arfanakis, and K. Maravilla. Hierarchical clustering to measure connectivity in fmri resting-state data. Magnetic Resonance Imaging, 20(4):305--317, 2002.Google ScholarCross Ref
- N. A. Dennis, et. al. Temporal lobe functional activity and connectivity in young adult carriers. Alzheimer's and Dementia, 6(4):303--311, 2010.Google ScholarCross Ref
- N. U. F. Dosenbach, et. al. Prediction of individual brain maturity using fmri. Science, 329(5997):1358--1361, 2010.Google ScholarCross Ref
- N. K. M. Faber, R. Bro, and P. K. Hopke, Recent developments in CANDECOMP/PARAFAC algorithms: A critical review, Chemometrics and Intelligent Laboratory Systems, 65 (2003)Google Scholar
- C. Genovese, N. Lazar, T. Nichols, Thresholding of statistical maps in functional neuroimaging using the false discovery rate. Neuroimage, 15, 870--8, (2002).Google ScholarCross Ref
- M. Greicius. Resting-state functional connectivity in neuropsychiatric disorders. Curr Opin Neurol, 21(4):424--430, 2008.Google ScholarCross Ref
- S. Huang, J. Li, L. Sun, J. Liu, T. Wu, K. Chen, A. Fleisher, E. Reiman and J. Ye Learning Brain Connectivity, NIPS 2009.Google Scholar
- T. Kolda and B. Bader, Tensor Decompositions and Applications, SIAM Review 2008. Google ScholarDigital Library
- P.-J. Lahaye, et. al. Functional connectivity: studying nonlinear, delayed interactions between bold signals. NeuroImage, 20(2):962--974, 2003.Google ScholarCross Ref
- F. D. Martino, et. al. Classification of fmri independent components using ic-fingerprints and support vector machine classifiers. NeuroImage, 34(1):177--194, 2007.Google ScholarCross Ref
- S. J. Peltier, T. A. Polk, and D. C. Noll. Detecting low-frequency functional connectivity in fmri using a self-organizing map (som) algorithm. Human Brain Mapping, 20(4):220--226, 2003.Google ScholarCross Ref
- M. Raichle, A. Snyder, A default mode of brain function: a brief history of an evolving idea. Neuroimage, 37, 1083--1090. 2007.Google ScholarCross Ref
- A. Stegman, Comparing independent component analysis and the PARAFAC model for artificial multi-subject fMRI data, Technical Report, University of Groningen, The Netherlands, Feb. 2007.Google Scholar
- C.M. Stonnington et. al., Predicting clinical scores from magnetic resonance scans in Alzheimer's disease, Neuroimage. 2010 Jul 15;51(4):1405--13.Google Scholar
- L. Sun, R. Patel, J. Liu, K. Chen, T. Wu, J. Li, E. Reiman, J. Ye, Mining Brain Region Connectivity for Alzheimer's Disease Study via Sparse Inverse Covariance Estimation, KDD 2009. Google ScholarDigital Library
- V. G. van de Ven, et. al. Functional connectivity as revealed by spatial independent component analysis of fmri measurements during rest. Human Brain Mapping, 22(3):165--178, 2004.Google ScholarCross Ref
- X. Wang, B. Qian, I. Davidson, Flexible Constrained Spectral Clustering: Algorithms and Applications, Journal of Knowledge Discovery and Data Mining (DMKD), November 2012. Google ScholarDigital Library
- J. L. Woodard, et. al.,Prediction of Cognitive Decline in Healthy Older Adults using fMRI, Journal of Alzheimers Disease. 2010 January 1; 21(3).Google Scholar
- P. Walker, I. Davidson, Exploring new methodologies for the analysis of fMRI following closed-head Injuries. In D. D. Schmorrow,Google Scholar
Index Terms
- Network discovery via constrained tensor analysis of fMRI data
Recommendations
PET and fMRI studies of the neural basis of speech perception
Special issue on the nature of speech perception (the psychophysics of speech perception III)Functional imaging (PET and fMRI) has made great advances in our understanding of the neural basis of auditory processing and speech perception. Here we review perceptual and sensory processing aspects of speech and hearing, as revealed by functional ...
Tensor Completion via Fully-Connected Tensor Network Decomposition with Regularized Factors
AbstractThe recently proposed fully-connected tensor network (FCTN) decomposition has a powerful ability to capture the low-rankness of tensors and has achieved great success in tensor completion. However, the FCTN decomposition-based method is highly ...
An MVPA method based on sparse representation for pattern localization in fMRI data analysis
A new MVPA method for fMRI data analysis.The ability of detecting subtle differences between experimental conditions.We localized two category-specific brain activation patterns corresponding to two experimental conditions.The two sets consisted of a ...
Comments