Loading...

Clustering method for fMRI activation detection using optimal number of clusters

Taalimi, A ; Sharif University of Technology | 2009

518 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/NER.2009.5109262
  3. Publisher: 2009
  4. Abstract:
  5. In this study, clustering based method for activation detection in functional magnetic resonance imaging (fMRI) is employed. Moreover, some features are obtained by fitting two models namely FIR filter and Gamma function, to hemodynamic response function (HRF). After applying clustering methods (that require number of clusters as an input) to feature space, our simulations show that number of clusters can affect activation detection significantly. Therefore a newly proposed clustering algorithm namely evolving neural gas (ENG) that gives optimal number of clusters is exploited. In addition to ENG, the result of four clustering algorithms namely k-means, fuzzy C-means, neural gas, and clara in different number of clusters are evaluated. The results show that the best activation detection is taken place using obtained optimal number of clusters. ©2009 IEEE
  6. Keywords:
  7. Activation detection ; Clustering ; Clustering methods ; Feature space ; fMRI ; Functional magnetic resonance imaging ; Fuzzy C mean ; Gamma function ; Hemodynamic response functions ; K-means ; Neural gas ; Number of clusters ; Optimal number ; Optimal number of clusters ; FIR filters ; Magnetic resonance imaging ; Optimization ; Clustering algorithms
  8. Source: 2009 4th International IEEE/EMBS Conference on Neural Engineering, NER '09, Antalya, 29 April 2009 through 2 May 2009 ; 2009 , Pages 171-174 ; 9781424420735 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/5109262