Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity.

Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algorithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification methods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The variation in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of principal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the dataset. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback.

Inverse retinotopy: inferring the visual content of images from brain activation patterns.

Traditional inference in neuroimaging consists in describing brain activations elicited and modulated by different kinds of stimuli. Recently, however, paradigms have been studied in which the converse operation is performed, thus inferring behavioral or mental states associated with activation images. Here, we use the well-known retinotopy of the visual cortex to infer the visual content of real or imaginary scenes from the brain activation patterns that they elicit. We present two decoding algorithms: an explicit technique, based on the current knowledge of the retinotopic structure of the visual areas, and an implicit technique, based on supervised classifiers. Both algorithms predicted the stimulus identity with significant accuracy. Furthermore, we extend this principle to mental imagery data: in five data sets, our algorithms could reconstruct and predict with significant accuracy a pattern imagined by the subjects.