Histopathology Image Categorization with Discriminative Dimension Reduction of Fisher Vectors

  • Yang SongEmail author
  • Qing Li
  • Heng Huang
  • Dagan Feng
  • Mei Chen
  • Weidong Cai
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9913)


In this paper, we present a histopathology image categorization method based on Fisher vector descriptors. While Fisher vector has been broadly successful for general computer vision and recently applied to microscopy image analysis, its feature dimension is very high and this could affect the classification performance especially when there is small amount of training images available. To address this issue, we design a dimension reduction algorithm in a discriminative learning model with similarity and representation constraints. In addition, to obtain the image-level Fisher vectors, we incorporate two types of local descriptors based on the standard texture feature and unsupervised feature learning. We use three publicly available datasets for experiments. Our evaluation shows that our overall approach achieves consistent performance improvement over existing approaches, our proposed discriminative dimension reduction algorithm outperforms the common dimension reduction techniques, and different local descriptors have varying effects on different datasets.


Gaussian Mixture Model Mantle Cell Lymphoma Local Descriptor Deep Belief Network Fisher Vector 
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.


  1. 1.
    Baudat, G., Anouar, F.: Generalized discriminant analysis using a kernel approach. Neural Comput. 12(10), 2385–2404 (2000)CrossRefGoogle Scholar
  2. 2.
    BenTaieb, A., Li-Chang, H., Huntsman, D., Hamarneh, G.: Automatic diagnosis of ovarian carcinomas via sparse multiresolution tissue representation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 629–636. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24553-9_77 CrossRefGoogle Scholar
  3. 3.
    Kandemir, M., Zhang, C., Hamprecht, F.A.: Empowering multiple instance histopathology cancer diagnosis by cell graphs. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 228–235. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-10470-6_29 Google Scholar
  4. 4.
    Keyvanrad, M.A., Homayounpour, M.M.: A brief survey on deep belief networks and introducing a new object oriented toolbox (DeeBNet) arXiv:1408.3264 (2014)
  5. 5.
    Li, W., Zhang, J., McKenna, S.J.: Multiple instance cancer detection by boosting regularised trees. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 645–652. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24553-9_79 CrossRefGoogle Scholar
  6. 6.
    Otálora, S., et al.: Combining unsupervised feature learning and riesz wavelets for histopathology image representation: application to identifying anaplastic medulloblastoma. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 581–588. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24553-9_71 CrossRefGoogle Scholar
  7. 7.
    Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15561-1_11 CrossRefGoogle Scholar
  8. 8.
    Shamir, L., Orlov, N., Eckley, D.M., Macura, T.J., Johnston, J., Goldberg, I.G.: Wndchrm - an open source utility for biological image analysis. Source Code Biol. Med. 3(1), 13 (2008)CrossRefGoogle Scholar
  9. 9.
    Sikka, K., Giri, R., Bartlett, M.: Joint clustering and classification for multiple instance learning. In: BMVC, pp. 1–12 (2015)Google Scholar
  10. 10.
    Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC, pp. 1–12 (2013)Google Scholar
  11. 11.
    Sparks, R., Madabhushi, A.: Explicit shape descriptors: novel morphologic features for histopathology classification. Med. Image Anal. 17(1), 997–1009 (2013)CrossRefGoogle Scholar
  12. 12.
    Vu, T.H., Mousavi, H.S., Monga, V., Rao, G., Rao, A.: Histopathological image classification using discriminative feature-oriented dictionary learning. IEEE Trans. Med. Imag. 35(3), 738–751 (2016)CrossRefGoogle Scholar
  13. 13.
    Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360–3367 (2010)Google Scholar
  14. 14.
    Xu, X., Lin, F., Ng, C., Leong, K.P.: Adaptive co-occurrence differential texton space for HEp-2 cells classification. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 260–267. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24574-4_31 CrossRefGoogle Scholar
  15. 15.
    Zhou, J., Lamichhane, S., Sterne, G., Ye, B., Peng, H.: BIOCAT: a pattern recognition platform for customizable biological image classification and annotation. BMC Bioinformatics 14, 291 (2013)CrossRefGoogle Scholar
  16. 16.
    Zhou, Y., Chang, H., Barner, K., Spellman, P., Parvin, B.: Classification of histology sections via multispectral convolutional sparse coding. In: CVPR, pp. 3081–3088 (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yang Song
    • 1
    Email author
  • Qing Li
    • 1
  • Heng Huang
    • 2
  • Dagan Feng
    • 1
  • Mei Chen
    • 3
    • 4
  • Weidong Cai
    • 1
  1. 1.BMIT Research Group, School of ITUniversity of SydneySydneyAustralia
  2. 2.Department of Computer Science and EngineeringUniversity of TexasArlingtonUSA
  3. 3.Computer Engineering DepartmentState University of New York at AlbanyAlbanyUSA
  4. 4.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations