A Model-Free Approach for Classification of fMRI Brain Images

This dissertation considers the problem of classifying subjects into predefined groups based on functional magnetic resonance imaging (fMRI) data. Classification of subjects into predefined groups, such as patient vs. control, based on their functional MRI data is a potentially useful procedure for ensuring homogeneous research samples and for clinical diagnostic purposes. Unlike other methods addressing the same question that are using either predefined regions of interest or statistical parametric maps, the proposed methodology uses preprocessed time series for the whole brain volume. Using a training set of two groups of subjects the presented methodology identifies spatio-temporal features that distinguish the groups and uses these features to categorize new subjects. The methodology is illustrated using simulations and in vivo data sets.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Psychology

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Shinkareva, Svetlana V.

Contributors dc:contributor

• Lawrence Hubert

• Biology, Neuroscience

Language dc:language

eng

Identifier

(MiAaPQ)AAI3199141

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/82097