Editorial: Brain decoding: Opportunities and challenges for pattern recognition

Authors:
Dimitri Van De Ville;Seong-Whan Lee
Affiliations:
Department of Radiology and Medical Informatics, University of Geneva, Switzerland and Institute of Bioengineering, Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland;-
Venue:
Pattern Recognition
Year:
2012

Citing 9
Cited 0

De-noising, phase ambiguity correction and visualization techniques for complex-valued ICA of group fMRI data

Pattern Recognition
Decoding visual brain states from fMRI using an ensemble of classifiers

Pattern Recognition
Bayesian hypothesis testing for pattern discrimination in brain decoding

Pattern Recognition
Model sparsity and brain pattern interpretation of classification models in neuroimaging

Pattern Recognition
A supervised clustering approach for fMRI-based inference of brain states

Pattern Recognition
Naive random subspace ensemble with linear classifiers for real-time classification of fMRI data

Pattern Recognition
Decoding stimulus-related information from single-trial EEG responses based on voltage topographies

Pattern Recognition
Brain computer interface control via functional connectivity dynamics

Pattern Recognition
Mutual information-based selection of optimal spatial-temporal patterns for single-trial EEG-based BCIs

Pattern Recognition

Quantified Score

Hi-index	0.02

Visualization

Abstract

The neuroimaging community heavily relies on statistical inference to explain measured brain activity given the experimental paradigm. Undeniably, this method has led to many results, but it is limited by the richness of the generative models that are deployed, typically in a mass-univariate way. Such an approach is suboptimal given the high-dimensional and complex spatiotemporal correlation structure of neuroimaging data. Over the recent years, techniques from pattern recognition have brought new insights into where and how information is stored in the brain by prediction of the stimulus or state from the data. Pattern recognition is intrinsically multivariate and the underlying models are data-driven. Moreover, the predictive setting is more powerful for many applications, including clinical diagnosis and brain-computer interfacing. This special issue features a number of papers that identify and tackle remaining challenges in this field. The specific problems at hand constitute opportunities for future research in pattern recognition and neurosciences.