Unifying Genetic Algorithm and Clustering Method for Recognizing Activated fMRI Time Series

  • Lin Shi
  • Pheng Ann Heng
  • Tien-Tsin Wong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3930)


In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.


fMRI Data Independent Component Analysis Cluster Centroid fMRI Time Series Empty Cluster 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bandettini, P.A., Jesmanowicz, A., Wong, E.C., Hyde, J.S.: Processing strategies for time-course data sets in functional mri of the human brain. Magn. Reson. Med. 30, 161–173 (1993)CrossRefGoogle Scholar
  2. 2.
    Sychra, J.J., Bandettini, P.A., Bhattacharya, N., Lin, Q.: Synthetic images by subspace transforms. i. principal components images and related filters. Med. Phys. 21, 193–201 (1994)CrossRefGoogle Scholar
  3. 3.
    Mckeown, M.J., Makeig, S., Brown, G.G., Jung, T.P., Kindermann, S.S., Bell, A.J., Sejnowski, T.J.: Analysis of fmri data by blind separation into independent spatial components. Hum. Brain Mapp. 6, 160–188 (1998)CrossRefGoogle Scholar
  4. 4.
    Krishna, K., Murty, M.: Genetic k-means algorithm. IEEE Trans. on Systems, Man and Cyber. Part B: Cybernetics 29, 433–439 (1999)CrossRefGoogle Scholar
  5. 5.
    Lu, Y., Lu, S., Fotouhi, F., Deng, Y., Brown, S.: Fast genetic k-means algorithm and its application in gene expression data analysis. Technical Report TR-DB-06-2003 (2003), http://www.cs.wayne.edu/~luyi/publication/tr0603.pdf
  6. 6.
    Tanabe, J., Miller, D., Tregellas, J., Freedman, R., Meyer, F.G.: Comparison of detrending methods for optimal fmri preprocessing. NeuroImage 15, 902–907 (2002)CrossRefGoogle Scholar
  7. 7.
    Ardekani, B.A., Kanno, I.: Statistical methods for detecting activated regions in functional mri of the brain. Magn Reson Imaging 16, 1217–1225 (1998)CrossRefGoogle Scholar
  8. 8.
    Goutte, C., Toft, P., Rostrup, E., Nielsen, F.A., Hansen, L.K.: On clustering fmri time series. NeuroImage 9, 298–310 (1999)CrossRefGoogle Scholar
  9. 9.
    Purdon, P., Solo, V., Brown, E.M., Weisskoff, R.: Functional mri signal modeling with spatial and temporal correlations. NeuroImage 14, 912–923 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Lin Shi
    • 1
  • Pheng Ann Heng
    • 1
  • Tien-Tsin Wong
    • 1
  1. 1.Department of Computer Science and EngineeringThe Chinese University of Hong KongShatin, NT, Hong Kong

Personalised recommendations