KCCA for fMRI Analysis
Hardoon, David R, Shawe-Taylor, John and Friman, Ola (2004) KCCA for fMRI Analysis. At Medical Image Understanding and Analysis, London, UK,
 | There is a more recent version of this item available. |
Download
Full text not available from this repository.
Description/Abstract
We use Kernel Canonical Correlation Analysis (KCCA) to infer brain activity in functional MRI by learning a semantic representation of fMRI brain scans and their associated activity signal. The semantic space provides a common representation and enables a comparison between the fMRI and the activity signal. We compare the approach against Canonical Correlation Analysis (CCA) by localising “activity” on a simulated null data set. Finally we present an approach to reconstruct an activity signal from a testing-set fMRI scans (both simulated and real), a method which allows us to validate our initial analysis.
| Item Type: | Conference or Workshop Item (Poster) |
|---|---|
| Additional Information: | Event Dates: 2004 |
| Divisions: | Faculty of Physical and Applied Science > Electronics and Computer Science |
| Item ID: | 260655 |
| Date Deposited: | 08 Mar 2005 |
| Last Modified: | 02 Mar 2012 12:40 |
| Contributors: | Hardoon, David R (Author) Shawe-Taylor, John (Author) Friman, Ola (Author) |
| Date: | 2004 |
| Additional Information: | Event Dates: 2004 |
| Status: | Published |
| Further Information: | Google Scholar |
| URI: | http://eprints.soton.ac.uk/id/eprint/260655 |
Available Versions of this Item
- KCCA for fMRI Analysis. (deposited 08 Mar 2005) [Currently Displayed]
Actions (login required)
 |
View Item |
