ISBI Tutorial 2012:

Brain Image Analysis

 
 

*** Prepare for the tutorial: hand-on tutorial set-up guide is online ***


Understanding how our brain performs cognition and perception is a challenging endeavor. Recently, machine learning approaches have emerged as an interesting direction to study our cognitive architecture based on imaging techniques such as functional magnetic resonance imaging (fMRI). The tutorial will present machine learning approaches in the analysis of neuroimaging data. We will first discuss necessary basics from machine learning, and will then present approaches that aim to capture and describe functional interaction patterns that emerge during specific cognitive processes and can span the entire brain. We will discuss multivariate analysis of functional response patterns, the study of functional connectivity and interaction, and the notion of references and atlases in group studies.


After covering the basic concepts of machine learning with neuroimaging data, the first part of the tutorial will focus on recent research moving beyond spatial reference systems towards decoupling function and anatomy, and related applications such as the study of reorganization and disease. The second part of the tutorial will continue on the theme of distributed activity, concentrating on different measures of functional connectivity, and discuss graph-based pattern recognition methods with applications to brain state and group discrimination. Finally, the last part of the tutorial will be a hands-on session presenting a state-of-the-art framework for machine learning with neuroimaging data, PyMVPA (www.pymvpa.org), where participants will see how to put into practice some of the methods presented during the workshop.

Functional interactions across the brain: multivariate pattern analysis methods and tools for fMRI

Programm:

Speakers:

Georg Langs             - CIR Lab, Medical University of Vienna; CSAIL, Massachusetts Institute of Technology

Jonas Richiardi         - School of Engineering, EPFL; Stanford

Emanuele Olivetti      - Medical Image Processing Laboratory, Ecole Polytechnique Fédérale de Lausanne and University of Geneva

  1. 14:30 Introduction

  2. 14:35 Talk: MVPA and Manifold learning: Functional patterns across cortex and subjects (Georg Langs)

  3. 15:20 Discussion

  4. 15:30 Talk: Modelling functional connectivity: connectivity measures and predictive models (Jonas Richiardi)

  5. 16:15 Discussion

  6. 16:30 Coffee break

  7. 17:00 Hands on tutorial: PyMVPA (Emanuele Olivetti)

Material:

Literature


More material for the tutorial will be posted here

Tutorial during ISBI 2012, May 1st, Barcelona