Jérôme Dockès

TL;DR: The authors proposed a multivariate model to predict the spatial distribution of neurological observations, given text describing an experiment, cognitive process, or disease, and the resulting meta-analytic tool, neuroquery, can ground hypothesis generation and data-analysis priors on a comprehensive view of published findings on the brain.

TL;DR: This work captures the relationships and neural correlates of 7547 neuroscience terms across 13 459 neuroimaging publications and proposes a new paradigm, focusing on prediction rather than inference, that predicts the spatial distribution of neurological observations, given text describing an experiment, cognitive process, or disease.

TL;DR: In this article, the authors propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms, which is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function.

TL;DR: In this article , the authors trained neural networks to predict cognitive labels on tens of thousands of brain images and successfully decoded more than 50 classes of mental processes on a large test set, which demonstrated that image-based meta-analyses can be undertaken at scale and with minimal manual data curation.