Abstract
Many current medical image analysis problems involve learning thousands or even millions of model parameters from extremely few samples. Employing sparse models provides an effective means for handling the curse of dimensionality, but other propitious properties beyond sparsity are typically not modeled. In this paper, we propose a simple approach, generalized sparse regularization (GSR), for incorporating domain-specific knowledge into a wide range of sparse linear models, such as the LASSO and group LASSO regression models. We demonstrate the power of GSR by building anatomically-informed sparse classifiers that additionally model the intrinsic spatiotemporal characteristics of brain activity for fMRI classification. We validate on real data and show how prior-informed sparse classifiers outperform standard classifiers, such as SVM and a number of sparse linear classifiers, both in terms of prediction accuracy and result interpretability. Our results illustrate the added-value in facilitating flexible integration of prior knowledge beyond sparsity in large-scale model learning problems.
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
Tibshirani, R.: Regression Shrinkage and Selection via the LASSO. J. Royal Stat. Soc. Series B 58, 267–288 (1996)
Zou, H., Hastie, T.: Regularization and Variable Selection via the Elastic Net. J. Royal Stat. Soc. Series B 67, 301–320 (2005)
Yuan, M., Lin, Y.: Model Selection and Estimation in Regression with Grouped Variables. J. Royal Stat. Soc. Series B 68, 49–67 (2006)
Sprechmann, P., Ramirez, I., Sapiro, G.: Collaborative Hierarchical Sparse Modeling. Technical report, arXiv:1003.0400v1 (2010)
Friedman, J., Hastie, T., Tibshirani, R.: A Note on the Group LASSO and a Sparse Group LASSO. Technical report, arXiv:1001.0736v1 (2010)
Jacob, L., Obozinski, G., Vert, J.P.: Group Lasso with overlaps and graph Lasso. In: Proc. Int. Conf. Mach. Learn., pp. 433–440 (2009)
Tibshirani, R., Taylor, J.: The Solution Path of the Generalized Lasso. Ann. Stat. (in press)
Tibshirani, R., Saunders, M., Rosset, S., Zhu, J., Knight, K.: Sparsity and Smoothness via the Fused Lasso. J. Royal Stat. Soc. Series B 67, 91–108 (2005)
Ng, B., Vahdat, A., Hamarneh, G., Abugharbieh, R.: Generalized sparse classifiers for decoding cognitive states in fMRI. In: Wang, F., Yan, P., Suzuki, K., Shen, D. (eds.) MLMI 2010. LNCS, vol. 6357, pp. 108–115. Springer, Heidelberg (2010)
Golub, T., Slonim, D., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J., Coller, H., Loh, M., Downing, J., Caligiuri, M.: Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring. Science 286, 531–536 (1999)
Mitchell, T.M., Shinkareva, S.V., Carlson, A., Chang, K.M., Malave, V.L., Mason, R.A., Just, M.A.: Predicting Human Brain Activity Associated with the Meanings of Nouns. Science 320, 1191–1195 (2008)
Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least Angle Regression. Ann. Stat. 32, 407–499 (2004)
van den Berg, E., Friedlander, M.P.: Probing the Pareto Frontier for Basis Pursuit Solu-tions. SIAM J. Sci. Comput. 31, 890–912 (2008)
Friedman, J., Hastie, T., Tibshirani, R.: Regularization Paths for Generalized Linear Models via Coordinate Descent. J. Stat. Software 33, 1–22 (2010)
Schmidt, M., Fung, G., Rosales, R.: Optimization Methods for L1-Regularization. Technical report, the University of British Columbia (2009)
Yamashita, O., Sato, M., Yoshioka, T., Tong, F., Kamitani, Y.: Sparse Estimation Auto-matically Selects Voxels Relevant for the Decoding of fMRI Activity Patterns. NeuroImage 42, 1414–1429 (2008)
Ryali, S., Supekar, K., Abrams, D.A., Menon, V.: Sparse Logistic Regression for Whole-brain Classification of fMRI Data. NeuroImage 51, 752–764 (2010)
Carroll, M.K., Cecchi, G.A., Rish, I., Garg, R., Rao, A.R.: Prediction and Interpretation of Distributed Neural Activity with Sparse Models. NeuroImage 44, 112–122 (2009)
van Gerven, M., Takashima, A., Heskes, T.: Selecting and Identifying Regions of Interest Using Groupwise Regularization. In: NIPS Workshop on New Directions in Statistical Learning for Meaningful and Reproducible fMRI Analysis (2008)
Michel, V., Eger, E., Keribin, C., Thirion, B.: Multi-class sparse bayesian regression for neuroimaging data analysis. In: Wang, F., Yan, P., Suzuki, K., Shen, D. (eds.) MLMI 2010. LNCS, vol. 6357, pp. 50–57. Springer, Heidelberg (2010)
Thirion, B., Flandin, G., Pinel, P., Roche, A., Ciuciu, P., Poline, J.B.: Dealing with the Shortcomings of Spatial Normalization: Multi-subject Parcellation of fMRI Datasets. Hum. Brain Mapp. 27, 678–693 (2006)
van Gerven, M., Cseke, B., de Lange, F.P., Heskes, T.: Efficient Bayesian Multivariate fMRI Analysis Using a Sparsifying Spatio-temporal Prior. NeuroImage 50, 150–161 (2010)
Cai, D., He, X., Han, J.: Spectral Regression: A Unified Approach for Sparse Subspace Learning. In: Proc. IEEE Int. Conf. Data Mining, pp. 73–82 (2007)
Yan, S., Xu, D., Zhang, B., Zhang, H.J., Yang, Q., Lin, S.: Graph Embedding and Exten-sion: A General Framework for Dimensionality Reduction. IEEE Trans. Pat. Ana. Machine Intell. 29, 40–50 (2007)
Fodor, J.A.: The Modularity of the Mind, pp. 2–47. MIT, Cambridge (1983)
Mitchell, T., Hutchinson, R., Niculescu, R., Pereira, F., Wang, X., Just, M., Newman, S.: Learning to Decode Cognitive States from Brain Images. Mach. Learn. 57, 145–175 (2004)
Liao, C.H., Worsley, K.J., Poline, J.B., Aston, A.D., Duncan, G.H., Evans, A.C.: Estimat-ing the Delay of the fMRI Response. NeuroImage 16, 593–606 (2002)
Manentiab, R., Cappab, S.F., Rossiniac, P.M., Miniussiad, C.: The Role of the Prefrontal Cortex in Sentence Comprehension: An rTMS Study. Cortex 44, 337–344 (2008)
Vandenberghe, R., Price, C., Wise, R., Josephs, O., Frackowiak, R.S.J.: Functional Anatomy of a Common Semantic System for Words and Pictures. Nature 383, 254–256 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ng, B., Abugharbieh, R. (2011). Generalized Sparse Regularization with Application to fMRI Brain Decoding. In: Székely, G., Hahn, H.K. (eds) Information Processing in Medical Imaging. IPMI 2011. Lecture Notes in Computer Science, vol 6801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22092-0_50
Download citation
DOI: https://doi.org/10.1007/978-3-642-22092-0_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22091-3
Online ISBN: 978-3-642-22092-0
eBook Packages: Computer ScienceComputer Science (R0)