Abstract
Prediction from medical images is a valuable aid to diagnosis. For instance, anatomical MR images can reveal certain disease conditions, while their functional counterparts can predict neuropsychiatric phenotypes. However, a physician will not rely on predictions by black-box models: understanding the anatomical or functional features that underpin decision is critical. Generally, the weight vectors of classifiers are not easily amenable to such an examination: Often there is no apparent structure. Indeed, this is not only a prediction task, but also an inverse problem that calls for adequate regularization. We address this challenge by introducing a convex region-selecting penalty. Our penalty combines total-variation regularization, enforcing spatial contiguity, and ℓ1 regularization, enforcing sparsity, into one group: Voxels are either active with non-zero spatial derivative or zero with inactive spatial derivative. This leads to segmenting contiguous spatial regions (inside which the signal can vary freely) against a background of zeros. Such segmentation of medical images in a target-informed manner is an important analysis tool. On several prediction problems from brain MRI, the penalty shows good segmentation. Given the size of medical images, computational efficiency is key. Keeping this in mind, we contribute an efficient optimization scheme that brings significant computational gains.
Chapter PDF
Similar content being viewed by others
Keywords
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
Baldassarre, L., Mourao-Miranda, J., Pontil, M.: Structured sparsity models for brain decoding from fMRI data. In: PRNI, p. 5 (2012)
Beck, A., Teboulle, M.: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans. Image Proc. (2009)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm with application to linear inverse problems. SIAM 2, 183–202 (2009)
Candes, E., Romberg, J.: Signal recovery from random projections. In: Wavelet Applications in Signal and Image Processing XI, SPIE. vol. 5674, p. 76 (2005)
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Transactions on Image Processing 10, 266 (2001)
Combettes, P.L., Pesquet, J.C.: Proximal splitting methods in signal processing. In: Fixed-Point Algorithms for Inverse Problems in Science and Engineering (2011)
Dohmatob, E., Gramfort, A., Thirion, B., Varoquaux, G.: Benchmarking solvers for TV-l1 least-squares and logistic regression in brain imaging. PRNI (2014)
Durrleman, S., Prastawa, M., Gerig, G., Joshi, S.: Optimal data-driven sparse parameterization of diffeomorphisms for population analysis. In: IPMI, p. 123 (2011)
Gramfort, A., Thirion, B., Varoquaux, G.: Identifying predictive regions from fMRI with TV-L1 prior. In: PRNI, pp. 17–20 (2013)
Grosenick, L., Klingenberg, B., Katovich, K., et al.: Interpretable whole-brain prediction analysis with graphnet. NeuroImage 72, 304 (2013)
Haxby, J., Gobbini, I., Furey, M., et al.: Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science 293, 2425 (2001)
Kandel, B.M., Wolk, D.A., Gee, J.C., Avants, B.: Predicting cognitive data from medical images using sparse linear regression. In: IPMI, p. 86 (2013)
Marcus, D.S., Wang, T.H., Parker, J., et al.: Open access series of imaging studies (OASIS): cross-sectional MRI data in young, middle aged, nondemented, and demented older adults. J. Cogn. Neurosci. 19, 1498 (2007)
Michel, V., Gramfort, A., Varoquaux, G.: other: Total variation regularization for fMRI-based prediction of behavior. IEEE Trans. Med. Im. 30, 1328 (2011)
Ng, B., Vahdat, A., Hamarneh, G., et al.: Generalized sparse classifiers for decoding cognitive states in fMRI. Machine Learning in Medical Imaging, p. 108 (2010)
Pock, T., Chambolle, A., Cremers, D., Bischof, H.: A convex relaxation approach for computing minimal partitions. In: CVPR, p. 810 (2009)
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Physica D: Nonlinear Phenomena 60, 259 (1992)
Schmidt, M., Roux, N.L., Bach, F.R.: Convergence rates of inexact proximal-gradient methods for convex optimization. In: NIPS, p. 1458 (2011)
Stonnington, C., Chu, C., Klöppel, S., et al.: Predicting clinical scores from magnetic resonance scans in alzheimer’s disease. Neuroimage 51, 1405 (2010)
Tom, S.M., Fox, C.R., Trepel, C., Poldrack, R.A.: The neural basis of loss aversion in decision-making under risk. Science 315(5811), 515–518 (2007)
Yamashita, O., Sato, M.A., Yoshioka, T., et al.: Sparse estimation automatically selects voxels relevant for the decoding of fMRI activity patterns. NeuroImage 42, 1414 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Eickenberg, M., Dohmatob, E., Thirion, B., Varoquaux, G. (2015). Grouping Total Variation and Sparsity: Statistical Learning with Segmenting Penalties. 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_84
Download citation
DOI: https://doi.org/10.1007/978-3-319-24553-9_84
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)