Advertisement

Large Margin Aggregation of Local Estimates for Medical Image Classification

  • Yang Song
  • Weidong Cai
  • Heng Huang
  • Yun Zhou
  • David Dagan Feng
  • Mei Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)

Abstract

Medical images typically exhibit complex feature space distributions due to high intra-class variation and inter-class ambiguity. Monolithic classification models are often problematic. In this study, we propose a novel Large Margin Local Estimate (LMLE) method for medical image classification. In the first step, the reference images are sub-categorized, and local estimates of the test image are computed based on the reference subcategories. In the second step, the local estimates are fused in a large margin model to derive the similarity level between the test image and the reference images, and the test image is classified accordingly. For evaluation, the LMLE method is applied to classify image patches of different interstitial lung disease (ILD) patterns on high-resolution computed tomography (HRCT) images. We demonstrate promising performance improvement over the state-of-the-art.

Keywords

Support Vector Machine Feature Vector Test Image Interstitial Lung Disease Reference Image 
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.

References

  1. 1.
    Depeursinge, A., Vargas, A., Platon, A., Geissbuhler, A., Poletti, P.A., Muller, H.: Building a reference multimedia database for interstitial lung diseases. Comput. Med. Imaging Graph. 36(3), 227–238 (2012)CrossRefGoogle Scholar
  2. 2.
    Dong, J., Xia, W., Chen, Q., Feng, J., Huang, Z., Yan, S.: Subcategory-aware object classification. In: CVPR, pp. 827–834 (2013)Google Scholar
  3. 3.
    Hoai, M., Zisserman, A.: Discriminative sub-categorization. In: CVPR, pp. 1666–1673 (2013)Google Scholar
  4. 4.
    Liao, S., Gao, Y., Shen, D.: Sparse patch based prostate segmentation in CT images. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 385–392. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Liu, J., Ji, S., Ye, J.: SLEP: sparse learning with efficient projections. Arizona State University (2009), http://www.public.asu.edu/~jye02/Software/SLEP/
  6. 6.
    Liu, M., Lu, L., Ye, X., Yu, S., Salganicoff, M.: Sparse classification for computer aided diagnosis using learned dictionaries. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 41–48. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  7. 7.
    Song, Y., Cai, W., Huang, H., Wang, X., Zhou, Y., Fulham, M., Feng, D.: Lesion detection and characterization with context driven approximation in thoracic FDG PET-CT images of NSCLC studies. IEEE Trans. Med. Imag. 33(2), 408–421 (2014)CrossRefGoogle Scholar
  8. 8.
    Song, Y., Cai, W., Zhou, Y., Feng, D.: Feature-based image patch approximation for lung tissue classification. IEEE Trans. Med. Imag. 32(4), 797–808 (2013)CrossRefGoogle Scholar
  9. 9.
    Wang, H., Nie, F., Huang, H., Risacher, S., Ding, C., Saykin, A.J., Shen, L.: ADNI: Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance. In: ICCV, pp. 557–562 (2011)Google Scholar
  10. 10.
    Weinberger, K., Saul, L.: Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research 10, 207–244 (2009)zbMATHGoogle Scholar
  11. 11.
    Xu, Y., Gao, X., Lin, S., Wong, D.W.K., Liu, J., Xu, D., Cheng, C., Cheung, C.Y., Wong, T.Y.: Automatic grading of nuclear cataracts from slit-lamp lens images using group sparsity regression. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 468–475. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Zhu, M., Martinez, A.: Subclass discriminant analysis. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1274–1286 (2006)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Yang Song
    • 1
  • Weidong Cai
    • 1
  • Heng Huang
    • 2
  • Yun Zhou
    • 3
  • David Dagan Feng
    • 1
  • Mei Chen
    • 4
  1. 1.BMIT Research Group, School of ITUniversity of SydneyAustralia
  2. 2.Computer Science and EngineeringUniversity of Texas at ArlingtonUSA
  3. 3.Johns Hopkins University School of MedicineUSA
  4. 4.Intel Science and Technology Center on Embedded ComputingCarnegie Mellon UniversityUSA

Personalised recommendations