Fast Optimal Transport Averaging of Neuroimaging Data
Knowing how the Human brain is anatomically and functionally organized at the level of a group of healthy individuals or patients is the primary goal of neuroimaging research. Yet computing an average of brain imaging data defined over a voxel grid or a triangulation remains a challenge. Data are large, the geometry of the brain is complex and the between subjects variability leads to spatially or temporally non-overlapping effects of interest. To address the problem of variability, data are commonly smoothed before performing a linear group averaging. In this work we build on ideas originally introduced by Kantorovich  to propose a new algorithm that can average efficiently non-normalized data defined over arbitrary discrete domains using transportation metrics. We show how Kantorovich means can be linked to Wasserstein barycenters in order to take advantage of the entropic smoothing approach used by . It leads to a smooth convex optimization problem and an algorithm with strong convergence guarantees. We illustrate the versatility of this tool and its empirical behavior on functional neuroimaging data, functional MRI and magnetoencephalography (MEG) source estimates, defined on voxel grids and triangulations of the folded cortical surface.
KeywordsfMRI Data Optimal Transport Gaussian Smoothing Nonnegative Measure Voxel Grid
A. Gramfort was supported by the ANR grant THALAMEEG, ANR-14-NEUC-0002-01. M. Cuturi gratefully acknowledges the support of JSPS young researcher A grant 26700002, the gift of a K40 card from NVIDIA and fruitful discussions with K.R. Müller. The work of G. Peyré has been supported by the European Research Council (ERC project SIGMA-Vision).
- 3.Benamou, J.D., Carlier, G., Cuturi, M., Nenna, L., Peyré, G.: Iterative bregman projections for regularized transportation problems. arXiv preprint arXiv:1412.5154 (2014)
- 4.Bertsimas, D., Tsitsiklis, J.: Introduction to linear optimization. Athena Scientific Belmont, Boston (1997)Google Scholar
- 5.Bonneel, N., Rabin, J., Peyré, G., Pfister, H.: Sliced and radon wasserstein barycenters of measures. J. Math. Imaging Vis. 51(1), 1–24 (2014)Google Scholar
- 6.Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv. Neural Inf. Process. Sys. 26, 2292–2300 (2013)Google Scholar
- 7.Cuturi, M., Doucet, A.: Fast computation of wasserstein barycenters. In: Proceedings of the 31st International Conference on Machine Learning (ICML-14) (2014)Google Scholar
- 8.Cuturi, M., Peyré, G., Rolet, A.: A smoothed dual approach for variational wasserstein problems. arXiv preprint arXiv:1503.02533 (2015)
- 14.Guittet, K.: Extended kantorovich norms: a tool for optimization. Technical repot 4402, INRIA (2002)Google Scholar
- 16.Henson, R.N., Wakeman, D.G., Litvak, V., Friston, K.J.: A parametric empirical bayesian framework for the EEG/MEG inverse problem: generative models for multisubject and multimodal integration. Front. Hum. Neuro. 5(76), 141–153 (2011)Google Scholar
- 19.Kanwisher, N., Mcdermott, J., Chun, M.M.: The fusiform face area: a module in human extrastriate cortex specialized for face perception. J. Neurosci. 17, 4302–4311 (1997)Google Scholar
- 23.Rubner, Y., Guibas, L., Tomasi, C.: The earth movers distance, multi-dimensional scaling, and color-based image retrieval. In: Proceedings of the ARPA Image Understanding Workshop, pp. 661–668 (1997)Google Scholar
- 27.Wipf, D., Ramirez, R., Palmer, J., Makeig, S., Rao, B.: Analysis of empirical bayesian methods for neuroelectromagnetic source localization. In: Proceedings of the Neural Information Processing Systems (NIPS) (2007)Google Scholar