RESUMO
Better acquisition protocols and analysis techniques are making it possible to use fMRI to obtain highly detailed visualizations of brain processes. In particular we focus on the reconstruction of natural images from BOLD responses in visual cortex. We expand our linear Gaussian framework for percept decoding with Gaussian mixture models to better represent the prior distribution of natural images. Reconstruction of such images then boils down to probabilistic inference in a hybrid Bayesian network. In our set-up, different mixture components correspond to different character categories. Our framework can automatically infer higher-order semantic categories from lower-level brain areas. Furthermore, the framework can gate semantic information from higher-order brain areas to enforce the correct category during reconstruction. When categorical information is not available, we show that automatically learned clusters in the data give a similar improvement in reconstruction. The hybrid Bayesian network leads to highly accurate reconstructions in both supervised and unsupervised settings.
RESUMO
With the advent of sophisticated acquisition and analysis techniques, decoding the contents of someone's experience has become a reality. We propose a straightforward linear Gaussian approach, where decoding relies on the inversion of properly regularized encoding models, which can still be solved analytically. In order to test our approach we acquired functional magnetic resonance imaging data under a rapid event-related design in which subjects were presented with handwritten characters. Our approach is shown to yield state-of-the-art reconstructions of perceived characters as estimated from BOLD responses. This even holds for previously unseen characters. We propose that this framework serves as a baseline with which to compare more sophisticated models for which analytical inversion is infeasible.