|
Informatics Report Series
|
|
|
|
|
|
|
|
|
| Title:Neural networks approach to clustering of activity in fMRI Data |
| Authors:
M Voultsidou
; S Dodel
; Michael Herrmann
|
| Date: 2005 |
| Publication Title:IEEE Transactions in Medical Imaging |
|
Publication Type:Journal Article
Publication Status:Published
|
|
Volume No:12:8
Page Nos:987-996
|
|
DOI:10.1109/TMI.2005.850542
ISBN/ISSN:0278-0062
|
- Abstract:
- Clusters of correlated activity in functional magnetic resonance imaging data can identify regions of interest and indicate interacting brain areas. Because the extraction of clusters is computationally complex, we apply an approximate method which is based on artificial neural networks. It allows one to find clusters of various degrees of connectivity ranging between the two extreme cases of cliques and connectivity components. We propose a criterion which allows to evaluate the relevanc of such structures based on the robustness with respect to parameter variations. Exploiting the intracluster correlations, we can show that regions of substantial correlation with an external stimulus can be unambiguously separated from other activity.
- Links To Paper
- No links available
- Bibtex format
- @Article{EDI-INF-RR-1150,
- author = {
M Voultsidou
and S Dodel
and Michael Herrmann
},
- title = {Neural networks approach to clustering of activity in fMRI Data},
- journal = {IEEE Transactions in Medical Imaging},
- year = 2005,
- volume = {12:8},
- pages = {987-996},
- doi = {10.1109/TMI.2005.850542},
- }
|
