Identifying a neuroanatomical signature of schizophrenia, reproducible across sites and stages, using machine learning with structured sparsity.

OBJECTIVE: Structural MRI (sMRI) increasingly offers insight into abnormalities inherent to schizophrenia. Previous machine learning applications suggest that individual classification is feasible and reliable and, however, is focused on the predictive performance of the clinical status in cross-sectional designs, which has limited biological perspectives. Moreover, most studies depend on relatively small cohorts or single recruiting site. Finally, no study controlled for disease stage or medication's effect. These elements cast doubt on previous findings' reproducibility. METHOD: We propose a machine learning algorithm that provides an interpretable brain signature. Using large datasets collected from 4 sites (276 schizophrenia patients, 330 controls), we assessed cross-site prediction reproducibility and associated predictive signature. For the first time, we evaluated the predictive signature regarding medication and illness duration using an independent dataset of first-episode patients. RESULTS: Machine learning classifiers based on neuroanatomical features yield significant intersite prediction accuracies (72%) together with an excellent predictive signature stability. This signature provides a neural score significantly correlated with symptom severity and the extent of cognitive impairments. Moreover, this signature demonstrates its efficiency on first-episode psychosis patients (73% accuracy). CONCLUSION: These results highlight the existence of a common neuroanatomical signature for schizophrenia, shared by a majority of patients even from an early stage of the disorder.

Scale-Free and Multifractal Time Dynamics of fMRI Signals during Rest and Task.

Scaling temporal dynamics in functional MRI (fMRI) signals have been evidenced for a decade as intrinsic characteristics of ongoing brain activity (Zarahn et al., 1997). Recently, scaling properties were shown to fluctuate across brain networks and to be modulated between rest and task (He, 2011): notably, Hurst exponent, quantifying long memory, decreases under task in activating and deactivating brain regions. In most cases, such results were obtained: First, from univariate (voxelwise or regionwise) analysis, hence focusing on specific cognitive systems such as Resting-State Networks (RSNs) and raising the issue of the specificity of this scale-free dynamics modulation in RSNs. Second, using analysis tools designed to measure a single scaling exponent related to the second order statistics of the data, thus relying on models that either implicitly or explicitly assume Gaussianity and (asymptotic) self-similarity, while fMRI signals may significantly depart from those either of those two assumptions (Ciuciu et al., 2008; Wink et al., 2008). To address these issues, the present contribution elaborates on the analysis of the scaling properties of fMRI temporal dynamics by proposing two significant variations. First, scaling properties are technically investigated using the recently introduced Wavelet Leader-based Multifractal formalism (WLMF; Wendt et al., 2007). This measures a collection of scaling exponents, thus enables a richer and more versatile description of scale invariance (beyond correlation and Gaussianity), referred to as multifractality. Also, it benefits from improved estimation performance compared to tools previously used in the literature. Second, scaling properties are investigated in both RSN and non-RSN structures (e.g., artifacts), at a broader spatial scale than the voxel one, using a multivariate approach, namely the Multi-Subject Dictionary Learning (MSDL) algorithm (Varoquaux et al., 2011) that produces a set of spatial components that appear more sparse than their Independent Component Analysis (ICA) counterpart. These tools are combined and applied to a fMRI dataset comprising 12 subjects with resting-state and activation runs (Sadaghiani et al., 2009). Results stemming from those analysis confirm the already reported task-related decrease of long memory in functional networks, but also show that it occurs in artifacts, thus making this feature not specific to functional networks. Further, results indicate that most fMRI signals appear multifractal at rest except in non-cortical regions. Task-related modulation of multifractality appears only significant in functional networks and thus can be considered as the key property disentangling functional networks from artifacts. These finding are discussed in the light of the recent literature reporting scaling dynamics of EEG microstate sequences at rest and addressing non-stationarity issues in temporally independent fMRI modes.

Hemodynamic-informed parcellation of fMRI data in a joint detection estimation framework.

Identifying brain hemodynamics in event-related functional MRI (fMRI) data is a crucial issue to disentangle the vascular response from the neuronal activity in the BOLD signal. This question is usually addressed by estimating the so-called hemodynamic response function (HRF). Voxelwise or region-/parcelwise inference schemes have been proposed to achieve this goal but so far all known contributions commit to pre-specified spatial supports for the hemodynamic territories by defining these supports either as individual voxels or a priori fixed brain parcels. In this paper, we introduce a joint parcellation-detection-estimation (JPDE) procedure that incorporates an adaptive parcel identification step based upon local hemodynamic properties. Efficient inference of both evoked activity, HRF shapes and supports is then achieved using variational approximations. Validation on synthetic and real fMRI data demonstrate the JPDE performance over standard detection estimation schemes and suggest it as a new brain exploration tool.

Anatomically informed interpolation of fMRI data on the cortical surface.

Analyzing functional magnetic resonance imaging (fMRI) data restricted to the cortical surface is of particular interest for two reasons: (1) to increase detection sensitivity using anatomical constraints and (2) to compare or use fMRI results in the context of source localization from magneto/electro-encephalography (MEEG) data, which requires data to be projected on the same spatial support. Designing an optimal scheme to interpolate fMRI raw data or resulting activation maps on the cortical surface relies on a trade-off between choosing large enough interpolation kernels, because of the distributed nature of the hemodynamic response, and avoiding mixing data issued from different anatomical structures. We propose an original method that automatically adjusts the level of such a trade-off, by defining interpolation kernels around each vertex of the cortical surface using a geodesic Voronoï diagram. This Voronoï-based interpolation method was evaluated using simulated fMRI activation maps, manually generated on an anatomical MRI, and compared with a more standard approach where interpolation kernels were defined as local spheres of radius r=3 or 5 mm. Several validation parameters were considered: the spatial resolution of the simulated activation map, the spatial resolution of the cortical mesh, the level of anatomical/functional data misregistration and the location of the vertices within the gray matter ribbon. Using an activation map at the spatial resolution of standard fMRI data, robustness to misregistration errors was observed for both methods, whereas only the Voronoï-based approach was insensitive to the position of the vertices within the gray matter ribbon.

Letter binding and invariant recognition of masked words: behavioral and neuroimaging evidence.

Fluent readers recognize visual words across changes in case and retinal location, while maintaining a high sensitivity to the arrangement of letters. To evaluate the automaticity and functional anatomy of invariant word recognition, we measured brain activity during subliminal masked priming. By preceding target words with an unrelated prime, a repeated prime, or an anagram made of the same letters, we separated letter-level and whole-word codes. By changing the case and the retinal location of primes and targets, we evaluated the invariance of those codes. Our results indicate that an invariant binding of letters into words is achieved unconsciously through a series of increasingly invariant stages in the left occipito-temporal pathway.