Manifold Learning for Biomarker Discovery in MR Imaging

  • Robin Wolz
  • Paul Aljabar
  • Joseph V. Hajnal
  • Daniel Rueckert
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6357)


We propose a framework for the extraction of biomarkers from low-dimensional manifolds representing inter- and intra-subject brain variation in MR image data. The coordinates of each image in such a low-dimensional space captures information about structural shape and appearance and, when a phenotype exists, about the subject’s clinical state. A key contribution is that we propose a method for incorporating longitudinal image information in the learned manifold. In particular, we compare simultaneously embedding baseline and follow-up scans into a single manifold with the combination of separate manifold representations for inter-subject and intra-subject variation. We apply the proposed methods to 362 subjects enrolled in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and classify healthy controls, subjects with Alzheimer’s disease (AD) and subjects with mild cognitive impairment (MCI). Learning manifolds based on both the appearance and temporal change of the hippocampus, leads to correct classification rates comparable with those provided by state-of-the-art automatic segmentation estimates of hippocampal volume and atrophy. The biomarkers identified with the proposed method are data-driven and represent a potential alternative to a-priori defined biomarkers derived from manual or automated segmentations.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chupin, M., Hammers, A., Liu, R., et al.: Automatic segmentation of the hippocampus and the amygdala driven by hybrid constraints: Method and validation. NeuroImage 46(3), 749–761 (2009)CrossRefGoogle Scholar
  2. 2.
    Freeborough, P.A., Fox, N.C.: The boundary shift integral: An accurate and robust measure of cerebral volume changes from registered repeat MRI. IEEE TMI 16(5), 623–629 (1997)Google Scholar
  3. 3.
    Fan, Y., Batmanghelich, N., Clark, C.M., Davatzikos, C.: Spatial patterns of brain atrophy in mci patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline. NeuroImage 39(4), 1731–1743 (2008)CrossRefGoogle Scholar
  4. 4.
    Gerardin, E., Chetelat, G., Chupin, M., et al.: Multidimensional classification of hippocampal shape features discriminates Alzheimer’s disease and mild cognitive impairment from normal aging. NeuroImage 47(4), 1476–1486 (2009)CrossRefGoogle Scholar
  5. 5.
    Chen, H.T., Chang, H.W., Liu, T.L.: Local discriminant embedding and its variants. In: CVPR, vol. II, pp. 846–853 (2005)Google Scholar
  6. 6.
    He, X., Yan, S., Hu, Y., et al.: Face recognition using laplacianfaces. IEEE Trans. Pattern Anal. Mach. Intell. 27 (2005)Google Scholar
  7. 7.
    Zhao, D.L., Lin, Z.C., Xiao, R., Tang, X.: Linear laplacian discrimination for feature extraction. In: CVPR, pp. 1–7 (2007)Google Scholar
  8. 8.
    Gerber, S., Tasdizen, T., Joshi, S.C., Whitaker, R.T.: On the manifold structure of the space of brain images. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5761, pp. 305–312. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Hamm, J., Davatzikos, C., Verma, R.: Efficient large deformation registration via geodesics on a learned manifold of images. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5761, pp. 680–687. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  10. 10.
    Tenenbaum, J.B., Freeman, W.T.: Separating style and content with bilinear models. Neural Computation 12, 1247–1283 (2000)CrossRefGoogle Scholar
  11. 11.
    Chang, W.Y., Chen, C.S., Hung, Y.P.: Analyzing facial expression by fusing manifolds. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 621–630. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)MATHCrossRefGoogle Scholar
  13. 13.
    Rueckert, D., Sonoda, L.I., Hayes, C., et al.: Nonrigid registration using free-form deformations: Application to breast MR images. IEEE TMI 18(8), 712–721 (1999)Google Scholar
  14. 14.
    Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Knowledge Discovery and Data Mining 2, 121–167 (1998)CrossRefGoogle Scholar
  15. 15.
    Wolz, R., Aljabar, P., Hajnal, J.V., Hammers, A., Rueckert, D.: LEAP: Learning embeddings for atlas propagation. NeuroImage 49(2), 1316–1325 (2010)CrossRefGoogle Scholar
  16. 16.
    Wolz, R., Heckemann, R.A., Aljabar, P., et al.: Measurement of hippocampal atrophy using 4D graph-cut segmentation: Application to ADNI. NeuroImage 52, 1009–1018 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Robin Wolz
    • 1
  • Paul Aljabar
    • 1
  • Joseph V. Hajnal
    • 2
  • Daniel Rueckert
    • 1
  1. 1.Department of ComputingImperial College LondonLondonUK
  2. 2.MRC Clinical Sciences CenterImperial College LondonLondonUK

Personalised recommendations