Online Program Home
  My Program

Abstract Details

Activity Number: 347 - Contributed Poster Presentations: Section on Statistics in Imaging
Type: Contributed
Date/Time: Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Imaging
Abstract #324236
Title: Image-On-Image Regression: a Spatial Bayesian Latent Factor Model for Predicting Task-Evoked Brain Activity Using Task-Free MRI
Author(s): Cui Guo*
Companies: University of Michigan
Keywords: Image-on-Image Regression ; Bayesian Modeling ; Latent Factor Analysis
Abstract:

Our brains usually have markedly different activity during task performance in almost all behavioral domains. It was thought that such individual differences in brain response are attributed to two possible factors, 1) differences in gross brain morphology and 2) different task strategy or cognitive processes. We assume that the individual differences in task-evoked brain activity are, to a great degree, inherent features of individual brain such that can be predicted from task-free measurements at rest. Then, a research question of interest is whether task-free MRI can be used to predict several task-evoked activity maps in multiple behavioral domains. To answer this question, we develop an image-on-image regression model to predict task-evoked image using task-free MRI. The two types of images are linked through a spatial Bayesian latent factor model. We first characterize the task-evoked image as linear combination of a high-dimentional basis sets. Then, a sparse representation of the task-evoked images is guaranteed through latent factor modeling of the basis coefficients. The continuous latent factors are fitted using selected predictor images under a linear regression model.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association