Journal of the Korean Physical Society

, Volume 61, Issue 7, pp 1148–1155

Comparison of distance measures for manifold learning: Application to Alzheimer’s brain scans

Research Papers


The scale of medical imaging data is growing rapidly and automated computer algorithms are well suited to analyze such data. Shape information can distinguish diseased scans from normal controls, but analyzing the data is difficult due to the high dimensionality of shape information. With manifold learning, shape analysis becomes more tractable in a low dimensional space. Some manifold learning methods, including multidimensional scaling (MDS), require a distance measure to quantify pair-wise dissimilarities between scans of interest. In this study, we compared two different distance measures combined with MDS to distinguish patients with Alzheimer’s disease (AD) and mild cognitive impairment (MCI) from normal control patients. The first distance measure is based on the displacement field, and the second distance measure is based on mutual information (MI). Shape quantification was applied to the brain scans of 25 normal, 25 AD, and 25 MCI patients. Use of the first distance measure resulted in an 18% error rate while use of the second distance measure resulted in a 46% error rate for classifying between patients with AD and normal patients. Application of MDS leads to a feature space, and we compared the MDS-induced feature space with the feature space induced from hippocampus volume, a traditionally used feature for distinguishing AD/MCI patients from normal patients.


Manifold learning Morphometry Shape quantification Multidimensional scaling Distance measure Alzheimer’s disease Mild cognitive impairment 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    U. Grenander and M. I. Miller, Q. Appl. Math. 4, 617 (1998).MathSciNetGoogle Scholar
  2. [2]
    J. Ashburner and K. J. Friston, NeuroImage 14, 1238 (2001).CrossRefGoogle Scholar
  3. [3]
    F. L. Bookstein, NeuroImage 14, 1454 (2001).CrossRefGoogle Scholar
  4. [4]
    C. Davatzikos, NeuroImage 23, 17 (2004).CrossRefGoogle Scholar
  5. [5]
    J. Ashburner, C. Hutton, R. Frackowiak, I. Johnsrude, C, Price and K. Friston, Hum. Brain Mapp. 6, 348 (1998).CrossRefGoogle Scholar
  6. [6]
    J. Ashburner and K. J. Friston, NeuroImage 11, 6 (2000).CrossRefGoogle Scholar
  7. [7]
    J. A. Lee and M. Verleysen, Nonlinear Dimensionality Reduction (Springer, 2007).Google Scholar
  8. [8]
    S. Gerber, T. Tasdizen, P. T. Fletcher, S. Joshi and R, Whitaker, Med. Image Anal. 14, 643 (2010).CrossRefGoogle Scholar
  9. [9]
    J. Hamm, D. H. Ye, R. Verma and C. Davatzikos, Med. Image Anal. 14, 633 (2010).CrossRefGoogle Scholar
  10. [10]
    W. S. Torgerson, Psychometrika 17, 401 (1952).MathSciNetMATHCrossRefGoogle Scholar
  11. [11]
    S. T. Roweis and L. K. Saul, Science 290, 2323 (2000).ADSCrossRefGoogle Scholar
  12. [12]
    J. B. Tenenbaum V. de Silva and J. C. Langford, Science 290, 5500 (2000).Google Scholar
  13. [13]
    R. Souvenir and R. Pless, Image Vision Comput. 25, 3 (2007).CrossRefGoogle Scholar
  14. [14]
    R. Wolz, P. Aljabar, J. V. Hajnal, A. Hammers and D. Rueckert, NeuroImage 49, 2 (2010).CrossRefGoogle Scholar
  15. [15]
    R. Brookmeyer, S. Gary and C. Kawas, Am. J. Public Health 88, 9 (1998).CrossRefGoogle Scholar
  16. [16]
    H. Park, J. Seo and ADNI, J. Neurosci. Methods 194, 380 (2011).CrossRefGoogle Scholar
  17. [17]
    Y. Fan, S. M. Resnick, X. Wu and C. Davatzikos, NeuroImage 39, 4 (2008).CrossRefGoogle Scholar
  18. [18]
    T. M. Cover and P. E. Hart, IEEE Trans. Inf. Theory 13, 1 (1967).CrossRefGoogle Scholar
  19. [19]
    X. Pennec, J. Math. Imaging Vision 25, 1 (2006).MathSciNetCrossRefGoogle Scholar
  20. [20]
    D. L. G. Hill, P. G. Batchelor, M. Holden and D. J. Hawkes, Phys. Med. Biol. 46, r1 (2001).ADSCrossRefGoogle Scholar
  21. [21]
    C. Meyer, J. L. Boes, B. Kim, P. H. Bland, K. R. Zasadny, P. V. Kison, K. Koral, K. A. Frey and R. L. Wahl, Med. Image Anal. 3, 195 (1997).CrossRefGoogle Scholar
  22. [22]
    M. I. Miller and L. Younes, Int. J. Comput. Vision 41, 1 (2001).CrossRefGoogle Scholar
  23. [23]
    W. M. Wells, P. Viola, H. Atsumi, S. Nakajima and R. Kikinis, Med. Img. Anal. 1, 1 (1996).CrossRefGoogle Scholar
  24. [24]
    E. Gerardin et al., NeuroImage 47, 4 (2009).CrossRefGoogle Scholar
  25. [25]
    M. W. Woolrich, S. Jbabdi, B. Patenaude, M. Chappell, S. Makni, T. Behrens, C. Beckmann, M. Jenkinson and S. M. Smith, NeuroImage 45, 1S (2009).CrossRefGoogle Scholar
  26. [26]
    V. de Silva and B. Tenebaum, Sparse Multidimensional Scaling Using Landmark Points (Stanford University, 2004).Google Scholar

Copyright information

© The Korean Physical Society 2012

Authors and Affiliations

  1. 1.School of Electronic Electrical EngineeringSungkyunkwan UniversitySuwonKorea

Personalised recommendations