Abstract Details
Activity Number:
|
284
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 5, 2014 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #313297
|
|
Title:
|
Clustering Approaches to Activation Detection in fMRI
|
Author(s):
|
Ranjan Maitra*+ and Wei-Chen Chen
|
Companies:
|
Iowa State University and University of Tennessee
|
Keywords:
|
mixtures of beta distributions ;
EM algorithm ;
segmentation ;
Bayesian Information Criterion ;
missing information ;
functional Magnetic Resonance Imaging
|
Abstract:
|
The past two decades have seen the development of functional Magnetic Resonance Imaging (fMRI) as a tool to noninvasively study the spatial characteristics and extent of human brain function. Preliminary statistical analysis relates the time-course MR sequences at a voxel to a stimulus and assessing significance of this relationship based on the p-values. Incorporating spatial context in the significance assessment is computationally challenging. We propose modeling the p-values as a mixture of beta distributions, while incorporating spatial context via the voxel coordinates. Parallel and accelerated Expectation-Maximization (EM) methods are used to perform computations in a practical setting and the Bayes Information Criterion (BIC) is used to determine the number of components in the best-fitting solution. The resulting segmentation is analyzed to specify common regions of activation, with promising results on simulation datasets and also on data from an fMRI study.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.