Neural networks approach to clustering of activity in fMRI data

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

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

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 approximative 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 relevance 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.
Original languageEnglish
Pages (from-to)987-996
Number of pages10
JournalIEEE Transactions on Medical Imaging
Issue number8
Publication statusPublished - 1 Aug 2005

Keywords / Materials (for Non-textual outputs)

  • biomedical MRI
  • brain
  • medical image processing
  • neural nets
  • pattern clustering
  • artificial neural networks
  • clustering
  • functional magnetic resonance imaging
  • interacting brain areas
  • intracluster correlations
  • Artificial neural networks
  • Brain
  • Computer networks
  • Data mining
  • Hopfield neural networks
  • Intelligent networks
  • Magnetic resonance imaging
  • Neural networks
  • Robustness
  • Signal processing
  • Cliques
  • Hopfield model
  • connectivity components
  • fMRI data
  • neural networks
  • Algorithms
  • Artificial Intelligence
  • Brain Mapping
  • Cluster Analysis
  • Electroencephalography
  • Humans
  • Image Enhancement
  • Image Interpretation, Computer-Assisted
  • Magnetic Resonance Imaging
  • Neural Networks (Computer)


Dive into the research topics of 'Neural networks approach to clustering of activity in fMRI data'. Together they form a unique fingerprint.

Cite this