Sparse Representation Using Block Decomposition for Characterization of Imaging Patterns

  • Keni Zheng
  • Sokratis MakrogiannisEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10530)


In this work we introduce sparse representation techniques for classification of high-dimensional imaging patterns into healthy and diseased states. We also propose a spatial block decomposition methodology that is used for training an ensemble of classifiers to address irregularities of the approximation problem. We first apply this framework to classification of bone radiography images for osteoporosis diagnosis. The second application domain is separation of breast lesions into benign and malignant. These are challenging classification problems because the imaging patterns are typically characterized by high Bayes error rate in the original space. To evaluate the classification performance we use cross-validation techniques. We also compare our sparse-based classification with state-of-the-art texture-based classification techniques. Our results indicate that decomposition into patches addresses difficulties caused by ill-posedness and improves original sparse classification.


  1. 1.
    Amaldi, E., Kann, V.: On the approximability of minimizing nonzero variables or unsatisfied relations in linear systems. Theoret. Comput. Sci. 209(1), 237–260 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Bartl, R., Frisch, B.: Osteoporosis: Diagnosis, Prevention, Therapy. Springer Science & Business Media, Heidelberg (2009)CrossRefGoogle Scholar
  3. 3.
    Candès, E.J., Romberg, J.K., Tao, T.: Stable signal recovery from incomplete and inaccurate measurements. Commun. Pure Appl. Math. 59(8), 1207–1223 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Candès, E.J., Tao, T.: Near-optimal signal recovery from random projections: Universal encoding strategies? IEEE Trans. Inf. Theory 52(12), 5406–5425 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Donoho, D.L.: For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution. Comm. Pure Appl. Math. 59(6), 797–829 (2004)CrossRefzbMATHGoogle Scholar
  6. 6.
    Donoho, D.L., Elad, M.: Optimally sparse representation in general (nonorthogonal) dictionaries via l1 minimization. Proc. Nat. Acad. Sci. 100(5), 2197–2202 (2003)CrossRefzbMATHGoogle Scholar
  7. 7.
    Ferlay, J., Héry, C., Autier, P., Sankaranarayanan, R.: Global burden of breast cancer. In: Li, C. (ed.) Breast Cancer Epidemiology, pp. 1–19. Springer, New York (2010). doi: 10.1007/978-1-4419-0685-4_1 Google Scholar
  8. 8.
    Qiao, L., Chen, S., Tan, X.: Sparsity preserving projections with applications to face recognition. Pattern Recogn. 43(1), 331–341 (2010)CrossRefzbMATHGoogle Scholar
  9. 9.
    Robere, R.: Interior point methods and linear programming. Technical report, University of Toronto (2012)Google Scholar
  10. 10.
    Smith, R.A., Cokkinides, V., Eyre, H.J.: American cancer society guidelines for the early detection of cancer, 2003. CA Cancer J. Clin. 53(1), 27–43 (2003)CrossRefGoogle Scholar
  11. 11.
    Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)CrossRefGoogle Scholar
  12. 12.
    Zhao, S.-H., Hu, Z.-P.: Occluded face recognition based on block-label and residual. Int. J. Artif. Intell. Tools 25(03), 1650019 (2016)CrossRefGoogle Scholar
  13. 13.
    Zhao, W., Xu, R., Hirano, Y., Tachibana, R., Kido, S.: A sparse representation based method to classify pulmonary patterns of diffuse lung diseases. Comput. Math. Methods Med. 2015, 567932 (2015)Google Scholar
  14. 14.
    Zheng, K., Makrogiannis, S.: Bone texture characterization for osteoporosis diagnosis using digital radiography. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1034–1037, August 2016Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Mathematical Sciences DepartmentDelaware State UniversityDoverUSA

Personalised recommendations