An Unbiased Penalty for Sparse Classification with Application to Neuroimaging Data
We present a novel formulation for discriminative anatomy detection in high dimensional neuroimaging data. While most studies solve this problem using mass univariate approaches, recent works show better accuracy and variable selection using a sparse classification model. Such methods typically use an \(l_1\) penalty for imposing sparseness and a graph net (GN) or a total variation (TV) penalty for ensuring spatial continuity and interpretability of the results. However it is known that the \(l_1\) and TV penalties have inherent bias that leads to less stable region detection and less accurate prediction. To overcome these limitations, we propose a novel variable selection method in the context of classification, based on the Smoothly Clipped Absolute Deviation (SCAD) penalty. We experimentally show superiority of three models based on the SCAD and SCADTV penalties when compared to the classical \(l_1\) and TV penalties in both simulated and real MRI data from a multiple sclerosis study.
KeywordsSparse classification Variable selection Localized statistics \(l_1\) optimization SCAD penalty
- 1.ANTS (2011). http://www.picsl.upenn.edu/ants/
- 7.Eickenberg, M., Dohmatob, E., Thirion, B., Varoquaux, G.: Grouping total variation and sparsity: statistical learning with segmenting penalties. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 685–693. Springer, Cham (2015). doi: 10.1007/978-3-319-24553-9_84 CrossRefGoogle Scholar
- 9.Gramfort, A., Thirion, B., Varoquaux, G.: Identifying predictive regions from fMRI with TV-L1 prior. In: International Workshop on PRNI, pp. 17–20 (2013)Google Scholar
- 11.Kandel, B., Avants, B., Gee, J., Wolk, D.: Predicting cognitive data from medical images using sparse linear regression. In: IPMI, pp. 86–97 (2013)Google Scholar
- 18.Wang, Y., Yin, W., Zeng, J.: Global convergence for ADMM in nonconvex nonsmooth optimization, arXiv:1551.06324