Mining Histopathological Images via Composite Hashing and Online Learning

  • Xiaofan Zhang
  • Lin Yang
  • Wei Liu
  • Hai Su
  • Shaoting Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)


With a continuous growing amount of annotated histopathological images, large-scale and data-driven methods potentially provide the promise of bridging the semantic gap between these images and their diagnoses. The purpose of this paper is to increase the scale at which automated systems can entail scalable analysis of histopathological images in massive databases. Specifically, we propose a principled framework to unify hashing-based image retrieval and supervised learning. Concretely, composite hashing is designed to simultaneously fuse and compress multiple high-dimensional image features into tens of binary hash bits, enabling scalable image retrieval with a very low computational cost. Upon a local data subset that retains the retrieved images, supervised learning methods are applied on-the-fly to model image structures for accurate classification. Our framework is validated thoroughly on 1120 lung microscopic tissue images by differentiating adenocarcinoma and squamous carcinoma. The average accuracy is 87.5% with only 17ms running time, which compares favorably with other commonly used methods.


Support Vector Machine Texture Feature Image Retrieval Online Learn Squamous Carcinoma 
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.
    Caicedo, J.C., Cruz, A., Gonzalez, F.A.: Histopathology image classification using bag of features and kernel functions. In: Combi, C., Shahar, Y., Abu-Hanna, A. (eds.) AIME 2009. LNCS, vol. 5651, pp. 126–135. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Cataluña, J.J.S., Perpiñá, M., Greses, J.V., Calvo, V., Padilla, J.D., París, F.: Cell type accuracy of bronchial biopsy specimens in primary lung cancer. CHEST 109(5) (1996)Google Scholar
  3. 3.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  4. 4.
    Edwards, S., Roberts, C., McKean, M., Cockburn, J., Jeffrey, R., Kerr, K.: Preoperative histological classification of primary lung cancer: accuracy of diagnosis and use of the non-small cell category. Journal of Clinical Pathology 53(7), 537–540 (2000)CrossRefGoogle Scholar
  5. 5.
    Freeman, D.L.: Harrison’s principles of internal medicine. JAMA: The Journal of the American Medical Association 286(8), 506 (2001)CrossRefGoogle Scholar
  6. 6.
    Kayser, G., Riede, U., Werner, M., Hufnagl, P., Kayser, K.: Towards an automated morphological classification of histological images of common lung carcinomas. Elec. J. Pathol. Histol. 8, 022–03 (2002)Google Scholar
  7. 7.
    Liu, J., Zhang, S., Liu, W., Zhang, X., Metaxas, D.: Scalable mammogram retrieval using anchor graph hashing. In: ISBI (2014)Google Scholar
  8. 8.
    Liu, W., Wang, J., Kumar, S., Chang, S.F.: Hashing with graphs. In: ICML, pp. 1–8 (2011)Google Scholar
  9. 9.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  10. 10.
    Makadia, A., Pavlovic, V., Kumar, S.: Baselines for image annotation. IJCV 90(1), 88–105 (2010)CrossRefGoogle Scholar
  11. 11.
    Mijović, Ž., Mihailović, D., Kostov, M.: Discriminant analysis of nuclear image variables in lung carcinoma. Facta Universitatis-Series: Medicine and Biology 15(1), 28–32 (2008)zbMATHGoogle Scholar
  12. 12.
    Siegel, R., Naishadham, D., Jemal, A.: Cancer statistics. CAJC 63(1), 11–30 (2013)CrossRefGoogle Scholar
  13. 13.
    Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: ICCV, pp. 1470–1477 (2003)Google Scholar
  14. 14.
    Tabesh, A., Teverovskiy, M., Pang, H.Y., Kumar, V.P., Verbel, D., Kotsianti, A., Saidi, O.: Multifeature prostate cancer diagnosis and gleason grading of histological images. TMI 26(10), 1366–1378 (2007)Google Scholar
  15. 15.
    Thunnissen, F., Diegenbach, P., Van Hattum, A., Tolboom, J., van der Sluis, D., Schaafsma, W., Houthoff, H., Baak, J.R.: Further evaluation of quantitative nuclear image features for classification of lung carcinomas. Pathology-Research and Practice 188(4), 531–535 (1992)CrossRefGoogle Scholar
  16. 16.
    Williams, C., Seeger, M.: Using the nyström method to speed up kernel machines. In: NIPS (2001)Google Scholar
  17. 17.
    Yang, L., Chen, W., Meer, P., Salaru, G., Goodell, L.A., Berstis, V., Foran, D.J.: Virtual microscopy and grid-enabled decision support for large-scale analysis of imaged pathology specimens. TITB 13(4), 636–644 (2009)Google Scholar
  18. 18.
    Zhang, S., Huang, J., Huang, Y., Yu, Y., Li, H., Metaxas, D.N.: Automatic image annotation using group sparsity. In: CVPR, pp. 3312–3319 (2010)Google Scholar
  19. 19.
    Zhang, X., Liu, W., Zhang, S.: Mining histopathological images via hashing-based scalable image retrieval. In: ISBI (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xiaofan Zhang
    • 1
  • Lin Yang
    • 2
  • Wei Liu
    • 3
  • Hai Su
    • 2
  • Shaoting Zhang
    • 1
  1. 1.Department of Computer ScienceUNC CharlotteUSA
  2. 2.Department of BiostatisticsUniversity of KentuckyLexingtonUSA
  3. 3.IBM T. J. Watson Research CenterYorktown HeightsUSA

Personalised recommendations