Hierarchical Constrained Local Model Using ICA and Its Application to Down Syndrome Detection

  • Qian Zhao
  • Kazunori Okada
  • Kenneth Rosenbaum
  • Dina J. Zand
  • Raymond Sze
  • Marshall Summar
  • Marius George Linguraru
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)


Conventional statistical shape models use Principal Component Analysis (PCA) to describe shape variations. However, such a PCA-based model assumes a Gaussian distribution of data. A model with Independent Component Analysis (ICA) does not require the Gaussian assumption and can additionally describe the local shape variation. In this paper, we propose a Hierarchical Constrained Local Model (HCLM) using ICA. The first or coarse level of HCLM locates the full landmark set, while the second level refines a relevant landmark subset. We then apply the HCLM to Down syndrome detection from photographs of young pediatric patients. Down syndrome is the most common chromosomal condition and its early detection is crucial. After locating facial anatomical landmarks using HCLM, geometric and local texture features are extracted and selected. A variety of classifiers are evaluated to identify Down syndrome from a healthy population. The best performance achieved 95.6% accuracy using support vector machine with radial basis function kernel. The results show that the ICA-based HCLM outperformed both PCA-based CLM and ICA-based CLM.


hierarchical constrained local model independent component analysis Down syndrome detection classification 


  1. 1.
    Cootes, T.F., et al.: Active Shape Models-Their Training and Application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  2. 2.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)Google Scholar
  3. 3.
    Cristinacce, D., Cootes, T.: Automatic feature localisation with constrained local models. Pattern Recognition 41, 3054–3067 (2008)CrossRefzbMATHGoogle Scholar
  4. 4.
    Üzümcü, M., Frangi, A.F., Sonka, M., Reiber, J.H.C., Lelieveldt, B.: ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 451–458. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  5. 5.
    Parker, S.E., et al.: Updated national birth prevalence estimates for selected birth defects in the United States, 2004–2006. Birth Defects Research Part A: Clinical and Molecular Teratology 88, 1008–1016 (2010)CrossRefGoogle Scholar
  6. 6.
    Benn, P.A.: Advances in prenatal screening for Down syndrome: I. general principles and second trimester testing. Clinica Chimica Acta; International Journal of Clinical Chemistry 323, 1–16 (2002)CrossRefGoogle Scholar
  7. 7.
    Sivakumar, S., Larkins, S.: Accuracy of clinical diagnosis in Down’s syndrome. Archives of Disease in Childhood 89, 691 (2004)CrossRefGoogle Scholar
  8. 8.
    Burçin, K., Vasif, N.V.: Down syndrome recognition using local binary patterns and statistical evaluation of the system. Expert Systems with Applications 38, 8690–8695 (2011)CrossRefGoogle Scholar
  9. 9.
    Saraydemir, Ş., et al.: Down Syndrome Diagnosis Based on Gabor Wavelet Transform. Journal of Medical Systems 36, 3205–3213 (2012)CrossRefGoogle Scholar
  10. 10.
    Cardoso, J.F.: High-order contrasts for independent component analysis. Neural Comput. 11, 157–192 (1999)CrossRefGoogle Scholar
  11. 11.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. I-511–I-518 (2001)Google Scholar
  12. 12.
    Ojala, T., et al.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 971–987 (2002)CrossRefGoogle Scholar
  13. 13.
    Cai, D., et al.: Unsupervised feature selection for multi-cluster data. Presented at the Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA (2010)Google Scholar
  14. 14.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20, 273–297 (1995)zbMATHGoogle Scholar
  15. 15.
    Denoeux, T.: A k-nearest neighbor classification rule based on Dempster-Shafer theory. IEEE Transactions on Systems, Man and Cybernetics 25, 804–813 (1995)CrossRefGoogle Scholar
  16. 16.
    Breiman, L.: Random Forests. Machine Learning 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar
  17. 17.
    Mika, S., et al.: Fisher discriminant analysis with kernels. In: Proceedings of the 1999 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing IX, 1999, pp. 41–48 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Qian Zhao
    • 1
  • Kazunori Okada
    • 2
  • Kenneth Rosenbaum
    • 3
  • Dina J. Zand
    • 3
  • Raymond Sze
    • 1
    • 4
  • Marshall Summar
    • 3
  • Marius George Linguraru
    • 1
  1. 1.Sheikh Zayed Institute for Pediatric Surgical InnovationChildren’s National Medical CenterWashingtonUSA
  2. 2.Computer Science DepartmentSan Francisco State UniversitySan FranciscoUSA
  3. 3.Division of Genetics and MetabolismChildren’s National Medical CenterWashingtonUSA
  4. 4.Department of RadiologyChildren’s National Medical CenterWashingtonUSA

Personalised recommendations