Nov 22

Meet metaMRI at NIPS’2016

MetaMRI partners will present several works at NIPS:

  • Learning brain regions via large-scale online structured sparse dictionary learning
    Elvis DOHMATOB*, Inria; Arthur Mensch, inria; Gaël Varoquaux, ; Bertrand Thirion,
  • Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain
    Timothy Rubin*, Indiana University; Sanmi Koyejo, UIUC; Michael Jones, Indiana University; Tal Yarkoni, University of Texas at Austin

Nov 01

Kick off of Neuroimaging power

The project aims at broaden the knowledge about accurate effect sizes and their variability in neuroimaging analysis and to provide intuition about effect sizes for different tasks and brain regions. It also aims at increasing the availability and ease the use of a variety of power analyses for neuroimaging data.

The project fund Joke Durnez (Inria Parietal, Stanford University).

Oct 01

Metacog project kick-off

This project funds the PhD thesis of J. Dockès.

The purpose of this thesis is to learn a semantic structure in cognitive terms from their occurrence in brain activations. This structure will simplify massive multi-label statistical-learning problems that arise in brain mapping by providing compact representations of cognitive concepts while capturing the imprecision on the definition these concepts.

Jul 23

Brain Imaging Data Structure

The Brain Imaging Data Structure (BIDS) is a standard for organizing and describing MRI datasets. The BIDS standard uses file formats compatible with existing software, unifies the majority of practices already common in the field, and captures the metadata necessary for most common data processing operations.

Work supported by MetaMRI. See

Jul 02

Formal Models of the Network Co-occurrence Underlying Mental Operations

Our paper in Plos Computational biology is out:

We contribute a multivariate statistical learning approach that can extract the major brain networks and quantify their configuration during various psychological tasks. The method is validated in two datasets by model-based generation of synthetic activity maps from recombination of shared network topographies. We demonstrate that task-specific neural activity patterns can be explained by plausible combinations of resting-state networks.

See for more information



Jun 01

BIS workshop: join the Nilearn coding sprint !

A Nilearn / Nistats coding sprint will take place in June 8-10 in Saclay and Paris. More information here and here.

Parietal is also organizing a round table at the Future en Seine event, on June 10th. More information here.

Feb 22

Parietal@Brainhack 2016: lots of good stuff for Nilearn !

The Paris 2016 Brainhack has been an opportunity for a demonstration of the visualization capabilities of Nilearn and many improvements: better visualization, better examples. In particular, we are getting an example on seed-based correlation, for instance for resting-state, and an encoding example, mapping receptor fields in the visual cortex.

Some longer terms projects have started, such as surface-based visualization and GLM API discussions (currently in Nistats).

Stay tuned for the next release!

Oct 27

Meet metaMRI at NIPS this year.

We will be presenting our recent work on the joint analysis of rest and task fMRI in Montreal.

Oct 21

Best Practices in Data Analysis and Sharing

Comments Sought on Best Practices in Data Analysis and Sharing (COBIDAS) White Paper, to which R. Poldrack and B. Thirion hhave contributed. More information here.


Jul 10

MetaMRI at the Nilearn/PyMNE coding sprint in Paris in July 2015

Software development is indeed an essential task for us. More information can be found here.

Older posts «