Abstract
This paper presents a novel tensor-based feature learning approach for whole-brain fMRI classification. Whole-brain fMRI data have high exploratory power, but they are challenging to deal with due to large numbers of voxels. A critical step for fMRI classification is dimensionality reduction, via feature selection or feature extraction. Most current approaches perform voxel selection based on feature selection methods. In contrast, feature extraction methods, such as principal component analysis (PCA), have limited usage on whole brain due to the small sample size problem and limited interpretability. To address these issues, we propose to directly extract features from natural tensor (rather than vector) representations of whole-brain fMRI using multilinear PCA (MPCA), and map MPCA bases to voxels for interpretability. Specifically, we extract low-dimensional tensors by MPCA, and then select a number of MPCA features according to the captured variance or mutual information as the input to SVM. To provide interpretability, we construct a mapping from the selected MPCA bases to raw voxels for localizing discriminating regions. Quantitative evaluations on challenging multiclass tasks demonstrate the superior performance of our proposed methods against the state-of-the-art, while qualitative analysis on localized discriminating regions shows the spatial coherence and interpretability of our mapping.
Chapter PDF
Similar content being viewed by others
Keywords
- Autism Spectrum Disorder
- Feature Selection
- Feature Selection Method
- fMRI Data
- Kernel Principal Component Analysis
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.
References
Batmanghelich, N., Dong, A., Taskar, B., Davatzikos, C.: Regularized tensor factorization for multi-modality medical image classification. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 17–24. Springer, Heidelberg (2011)
Chen, M., et al.: Survey of encoding and decoding of visual stimulus via fMRI: An image analysis perspective. Brain Imaging and Behavior 8(1), 7–23 (2014)
Chou, C.A., et al.: Voxel selection framework in multi-voxel pattern analysis of fMRI data for prediction of neural response to visual stimuli. IEEE Transactions on Medical Imaging 33(4), 925–934 (2014)
Cuingnet, R., Rosso, C., Lehéricy, S., Dormont, D., Benali, H., Samson, Y., Colliot, O.: Spatially regularized SVM for the detection of brain areas associated with stroke outcome. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part I. LNCS, vol. 6361, pp. 316–323. Springer, Heidelberg (2010)
Ecker, C., et al.: Investigating the predictive value of whole-brain structural MR scans in autism: A pattern classification approach. NeuroImage 49(1), 44–56 (2010)
Irimia, A., Van Horn, J.D.: Systematic network lesioning reveals the core white matter scaffold of the human brain. Frontiers in Human Neuroscience 8, 1–14 (2014)
Kampa, K., Mehta, S., et al.: Sparse optimization in feature selection: application in neuroimaging. Journal of Global Optimization 59(2-3), 439–457 (2014)
Lu, H., Plataniotis, K.N., Venetsanopoulos, A.: Multilinear Subspace Learning: Dimensionality Reduction of Multidimensional Data. CRC Press (2013)
Lu, H., Plataniotis, K.N., et al.: MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Networks 19(1), 18–39 (2008)
McKeown, M.J., et al.: Local linear discriminant analysis (LLDA) for group and region of interest (ROI)-based fMRI analysis. NeuroImage 37(3), 855–865 (2007)
Mitchell, T.M., Shinkareva, S.V., et al.: Predicting human brain activity associated with the meanings of nouns. Science 320(5880), 1191–1195 (2008)
Mourão-Miranda, J., et al.: Classifying brain states and determining the discriminating activation patterns: Support vector machine on functional MRI data. NeuroImage 28(4), 980–995 (2005)
Mourão-Miranda, J., et al.: The impact of temporal compression and space selection on SVM analysis of single-subject and multi-subject fMRI data. NeuroImage 33(4), 1055–1065 (2006)
Mwangi, B., Tian, T.S., Soares, J.C.: A review of feature reduction techniques in neuroimaging. Neuroinformatics 12(2), 229–244 (2013)
Rasmussen, P.M., et al.: Model sparsity and brain pattern interpretation of classification models in neuroimaging. Pattern Recognition 45(6), 2085–2100 (2012)
Retico, A., Bosco, P., et al.: Predictive models based on support vector machines: Whole-brain versus regional analysis of structural MRI in the alzheimer’s disease. Journal of Neuroimaging, 1–12 (2014)
Ryali, S., Supekar, K., Abrams, D.A., Menon, V.: Sparse logistic regression for whole-brain classification of fMRI data. NeuroImage 51(2), 752–764 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Song, X., Meng, L., Shi, Q., Lu, H. (2015). Learning Tensor-Based Features for Whole-Brain fMRI Classification. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015. MICCAI 2015. Lecture Notes in Computer Science(), vol 9349. Springer, Cham. https://doi.org/10.1007/978-3-319-24553-9_75
Download citation
DOI: https://doi.org/10.1007/978-3-319-24553-9_75
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24552-2
Online ISBN: 978-3-319-24553-9
eBook Packages: Computer ScienceComputer Science (R0)