Multi-site fMRI studies face the challenge that the pooling introduces systematic non-biological site-specific variance due to hardware, software, and environment. In this paper, we propose to reduce site-specific variance in the estimation of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data via a simple yet effective matrix factorization while preserving biologically relevant variations. Our method leverages unsupervised adversarial learning to improve the reproducibility of the components. Experiments on simulated datasets display that the proposed method can estimate components with higher accuracy and reproducibility, while preserving age-related variation on a multi-center clinical data set.

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain function into a universal cognitive system that relates mental operations/cognitive processes/psychological tasks to brain networks? We cast this challenge in a machine-learning approach to predict conditions from statistical brain maps across different studies. For this, we leverage multi-task learning and multi-scale dimension reduction to learn low-dimensional representations of brain images that carry cognitive information and can be robustly associated with psychological stimuli. Our multi-dataset classification model achieves the best prediction performance on several large reference datasets, compared to models without cognitive-aware low-dimension representations; it brings a substantial performance boost to the analysis of small datasets, and can be introspected to identify universal template cognitive concepts.

Multi-site fMRI studies face the challenge that the pooling introduces systematic non-biological site-specific variance due to hardware, software, and environment. In this paper, we propose to reduce site-specific variance in the estimation of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data via a simple yet effective matrix factorization while preserving biologically relevant variations. Our method leverages unsupervised adversarial learning to improve the reproducibility of the components. Experiments on simulated datasets display that the proposed method can estimate components with higher accuracy and reproducibility, while preserving age-related variation on a multi-center clinical data set.

This paper proposes a new model architecture dedicated to multi-dataset brain decoding classification. Multi-dataset classification is a tricky problem in machine learning, especially when the number of samples is particularly small. In order to solve this problem, the author(s) employed the ideas of knowledge aggregation and transfer learning. The main idea of this paper is interesting but my main concerts are on the limited novelty compared to the previous work. Furthermore, I do not find any references or discussions in order to present the limitation of the proposed methods. Some reconstructive comments are listed as follows: 1.

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain function into a universal cognitive system that relates mental operations/cognitive processes/psychological tasks to brain networks? We cast this challenge in a machine-learning approach to predict conditions from statistical brain maps across different studies. For this, we leverage multi-task learning and multi-scale dimension reduction to learn low-dimensional representations of brain images that carry cognitive information and can be robustly associated with psychological stimuli.

The discovery of major software flaws could render thousands of fMRI brain studies inaccurate. The use of fMRI is a common method for scanning the brain in neuroscience and psychology experiments. To make sense of the data produced, researchers sometimes use a technique called spatial autocorrelation to identify areas of the brain that appear to "light up" during particular tasks or experiences. But some software flaws in the popular fMRI data analysis packages SPM, FSL and AFNI meant this technique routinely produced false positives, resulting in errors 50 per cent of the time or more. Anders Eklund and Hans Knutsson at Linköping University in Sweden and Thomas Nichols at the University of Warwick, UK, calculated this by analysing brain data from a collaborative open fMRI project called 1000 Functional Connectomes.

The most sophisticated, widely adopted, and important tool for looking at living brain activity actually does no such thing. Called functional magnetic resonance imaging, what it really does is scan for the magnetic signatures of oxygen-rich blood. Blood indicates that the brain is doing something, but it's not a direct measure of brain activity. Which is to say, there's room for error. That's why neuroscientists use special statistics to filter out noise in their fMRIs, verifying that the shaded blobs they see pulsing across their computer screens actually relate to blood flowing through the brain.

We present a model that describes the structure in the responses of different brain areas to a set of stimuli in terms of stimulus categories" (clusters of stimuli) and "functional units" (clusters of voxels). We assume that voxels within a unit respond similarly to all stimuli from the same category, and design a nonparametric hierarchical model to capture inter-subject variability among the units. The model explicitly captures the relationship between brain activations and fMRI time courses. A variational inference algorithm derived based on the model can learn categories, units, and a set of unit-category activation probabilities from data. When applied to data from an fMRI study of object recognition, the method finds meaningful and consistent clusterings of stimuli into categories and voxels into units."