TUTORIAL 4
NILEARN
Gaël Varoquaux, Parietal INRIA
Danilo Bzdok, Uniklinik RWTH Aachen
There is growing interest in data-driven analysis, multivariate statistics and predictive modeling for neuroimaging. Datasets are also constantly growing in sample size, resolution, and complexity. Nilearn is a Python package designed to address these new challenges in contemporary data analysis for imaging neuroscience. It provides state-of-the-art machine-learning methods for convenient pre-processing, analysis, and visualization of various types of neuroimaging results (i.e., experimental fMRI, VBM, and resting-state correlations). The tutorial will cover: (i) plotting and image manipulation with nilearn; (ii) decoding and predictive models; (iii) functional connectivity and resting-state data analysis.
More details, including the full two-day tutorial agenda, are available here.
TUTORIAL 2
Brain Data Sharing
Michael Hanke, University of Magdeburg
Christof Gorgolewski, Stanford University
Vittorio Iacovella, Fondazione Bruno Kessler
To publish brain data related to cognitive neuroscience (e.g. neuroimaging, electrophysiological, behavioral data) is becoming more and more important within the community: (i) it simplifies the re-use of the data, within and outside the lab; (ii) it facilitates reviewing of how the data were analyzed, after publishing; (iii) it increases the amount of accessible information for the whole community. However, just a small part of the community includes this activity within their research routine. Many people avoid publishing data just because they do not know how to do it. Given that it is not completely clear how this activity is rewarded, to spend time in learning how to do is considered not useful. Here we propose a tutorial where we first explain implications of sharing the data, describing the most common projects, including openfmri.org, illustrate data management standards, and present easy-to-use tools for versioning and collaboratively share the data. Then we practically guide participants through actual preparation and sharing of several different dataset we made ready for practicing. At the end of the tutorial, participants should have acquired the skills to re-organize and publish a dataset, back in the lab.
More details, including the full day tutorial agenda, are available here
Brain Network Analysis
Brain graph analysis provides a new suite of tools for the scientific study of brain connectivity and its association to behaviour, physiology, and diseases. Accumulating evidence is suggesting that neuropsychiatric disorders are linked to abnormal brain connectivity, and inter-subject differences in behaviour can be partially explained by variability in brain connectivity. This tutorial will cover a range of classic and modern methods for estimation, classification, and inference on brain graphs. The six main areas of focuses are: (i) estimation of connectivity graphs, (ii) classification using brain connectivity, (iii) statistical inference to identify relevant brain connections, (iv) kernels methods for brain graph inference, and (v) estimation and evaluation of time varying brain connectivity. Each section will include hands-on examples.
More details, including the full day tutorial agenda, are available here
Bernard Ng, University of British Columbia
Sanmi Koyejo, Stanford University
Sandro Vega Pons, Fondazione Bruno Kessler
TUTORIAL 1
TUTORIAL 3
Nickolas Oosterhof, University of Trento
CoSmoMVPA is a multi-modal, multi-variate pattern analysis (MVPA) toolbox for cognitive neuroscientists. It runs on Matlab and GNU Octave. CoSmoMVPA provides simple, lightweight implementations of the most common types of MVPA of cognitive neuroscience data, such as classification with cross-validation, correlations, representational similarity analysis, and generalization over time. It supports most common fMRI (including NIFTI, ANALYZE, BrainVoyager, AFNI, GIFTI) and MEEG (FieldTrip, EEGLab) data formats, and handles fMRI volumetric, fMRI surface-based, and MEEG data through a uniform data structure. The tutorial will present examples of use of searchlights in the volume, on the surface, over sensors, time bins, and frequency bands, and any combinations of these (e.g. sensor by time by frequency). An hands-on section will include practical exercises on both fMRI and MEG data, and some best-practice methods for multiple-comparison correction like Threshold-Free Cluster Enhancement. CoSMoMVPA is distributed as Free/Open Source Software (MIT License)
More details, including the full two-day tutorial agenda, are available here.
CoSMoMVPA
TUTORIAL 5
Alexandre Gramfort, CNRS, Telecom Paristech, Université Paris-Saclay
MNE (http://martinos.org/mne) is a software package for processing magnetoencephalography (MEG) and electroencephalography (EEG) data. It provides a comprehensive workflow for data preprocessing, forward modeling (with FreeSurfer) using boundary element models (BEM), source imaging using distributed source models, time–frequency analysis, non-parametric and multivariate statistics, decoding and connectivity measures. All analyses can be conducted either in the sensor or in the source space. The aim of this tutorial is to present what MNE can do, starting from raw data using the Python programming language. The tutorial will be hands on based on IPython notebooks so the attendees can run the full analysis on their machines and experiment with the tool, eventually on their own MEG or EEG data.
More details, including the full two-day tutorial agenda, are available here.