Analysis of correlated activity in fMRI data by artificial neural networks

M. Voultsidou, S. Dodel, J. M. Herrmann

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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 languageEnglish
Title of host publicationBiomedical Imaging: Nano to Macro, 2004. IEEE International Symposium on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages4
ISBN (Print)0-7803-8388-5
Publication statusPublished - 1 Apr 2004


  • 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


Dive into the research topics of 'Analysis of correlated activity in fMRI data by artificial neural networks'. Together they form a unique fingerprint.

Cite this