Abstract / Description of output
Clusters of correlated activity in fMRI data can identify regions of interest and indicate interacting brain areas. Because the extraction of clusters is computationally complex, we apply an approximative method which is based on Hopfield networks. It allows to find clusters of various degrees of connectivity ranging between the two extreme cases of cliques and connectivity components. Further we propose a criterion which allows to evaluate the relevance of such structures based on the robustness with respect to parameter variations.
Original language | English |
---|---|
Title of host publication | Biomedical Imaging: Nano to Macro, 2004. IEEE International Symposium on |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 872-875 |
Number of pages | 4 |
Volume | 1 |
ISBN (Print) | 0-7803-8388-5 |
DOIs | |
Publication status | Published - 1 Apr 2004 |
Keywords / Materials (for Non-textual outputs)
- Hopfield neural nets
- biomedical MRI
- brain
- medical computing
- statistical analysis
- Hopfield networks
- artificial neural networks
- correlated activity
- functional magnetic resonance imaging
- interacting brain areas
- Artificial intelligence
- Artificial neural networks
- Character generation
- Chromium
- Intelligent networks
- Variable speed drives