Schizophrenia is a complex psychiatric disorder that has eluded a characterization in terms of local abnormalities of brain activity, and is hypothesized to affect the collective, ``emergent working of the brain. We propose a novel data-driven approach to capture emergent features using functional brain networks [Eguiluzet al] extracted from fMRI data, and demonstrate its advantage over traditional region-of-interest (ROI) and local, task-specific linear activation analyzes. Our results suggest that schizophrenia is indeed associated with disruption of global, emergent brain properties related to its functioning as a network, which cannot be explained by alteration of local activation patterns. Moreover, further exploitation of interactions by sparse Markov Random Field classifiers shows clear gain over linear methods, such as Gaussian Naive Bayes and SVM, allowing to reach 86% accuracy (over 50% baseline - random guess), which is quite remarkable given that it is based on a single fMRI experiment using a simple auditory task.

The acquisition of brain images in fMRI yields rich topographic information about the functional structure of the brain. However, these descriptions are limited by strong inter-subject variability. A recent approach to represent the gross functional architecture across the population as seen in fMRI consists in automatically defining accross-subjects brain parcels. This technique yields large-scale inter-subject correspondences while allowing some spatial relaxation in the alignment of the brains. We address here the open question of an optimal parameterization (number of parcels) of brain parcellations using information theoretic criteria and cross-validation. Moreover, a finer analysis of variance components enables us to better characterize intra- and inter-subject variability sources in parcellation models.