[Colloquium] TTIC Colloquium: Thomas Shultz, Max Planck Institute for Intelligent Systems

[Liv Leader]

REMINDER:

When:     Tuesday, October 23 @ 11 a.m.

Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room #526

Who:       Thomas Shultz, Max Planck Institute for Intelligent Systems

Title:       Mathematical Modeling and Machine Learning in Brain Diffusion
MRI

Abstract: Diffusion MRI is a modern imaging modality that is particularly
suited
for investigating the nerve fiber bundles that connect different regions
of the human brain and thus is one of the key technologies in the
ongoing Human Connectome Project. In this talk, I will discuss some of
the computational challenges inherent in drawing inference from the
large and complex data sets created by this technique.

The first part of the talk will consider the problem of reconstructing
the trajectories of major nerve fiber bundles from the data, known as
tractography or fiber tracking. I will introduce a mathematical model
that is based on higher-order tensors and is able to deal with voxels
that contain crossing fiber populations, and I will discuss its
advantages over alternative models.

The second part of the talk will focus on the use of machine learning in
the analysis of brain diffusion MRI. This will include the training of a
classifier for model selection and a discussion of the current state of
the art in trying to achieve automated diagnosis based on diffusion
imaging data.

http://people.kyb.tuebingen.mpg.de/tschultz/

Host: Samory Kpotufe, samory at ttic.edu

-- 
Liv Leader
Director of Human Resources and International Affairs

Toyota Technological Institute Chicago
6045 S Kenwood Ave
Chicago, IL 60637
Phone- (773) 702-5033
Fax-     (773) 834-9881
Email-  lleader at ttic.edu
Web-   www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20121022/ad790b50/attachment.htm