University of Illinois Urbana-Champaign

Statistical methods for fMRI data analysis

Xia, Jing

Content Files
Xia_Jing.pdf

Permalink

https://hdl.handle.net/2142/24259

Description

Title
Statistical methods for fMRI data analysis
Author(s)
Xia, Jing
Issue Date
2011-05-25T14:56:20Z
Director of Research (if dissertation) or Advisor (if thesis)
Wang, Michelle Y.
Doctoral Committee Chair(s)
Wang, Michelle Y.
Committee Member(s)
  • Liang, Feng
  • Simpson, Douglas G.
  • Marden, John I.
Department of Study
Statistics
Discipline
Statistics
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Date of Ingest
2011-05-25T14:56:20Z
Keyword(s)
  • Functional magnetic resonance imaging (fMRI)
  • Functional Activation
  • Functional Connectivity
  • Bayesian
Abstract
Since the early 1990s, functional magnetic resonance imaging (fMRI) has dominated the brain mapping field and it has been proved a powerful tool for mapping human brain functions. The fMRI is a high spatial-temporal resolution medical-imaging modality, which means the data structure is complicated and the data size is huge. These features of fMRI data pose some challenges to traditional statistical methods which focus on data with smal sample size and simple data structure. The functional activation detection and functional connectivity network analysis by using fMRI are two important research topics in the neuroscience. In this work, we present three different statistical methods, corresponding to three chapters, for the activation detection and network discovery. In the first part, we present a spatial Bayesian method for simultaneous activation detection and hemodynamic response function (HRF) estimation; in the second part, we propose a model based clustering method to detect the functional connectivity network; in the third part, we present a general and novel statistical framework for robust and more complete estimation of brain functional connectivity based on correlation analysis and hypothesis testing. The complicated data features are taken into account in the three algorithms.
Graduation Semester
2011-05
Permalink
http://hdl.handle.net/2142/24259
Copyright and License Information
Copyright 2011 Jing Xia

Owning Collections

Dissertations and Theses - Statistics
Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois