Empowering Multiple Instance Histopathology Cancer Diagnosis by Cell Graphs

  • Melih Kandemir
  • Chong Zhang
  • Fred A. Hamprecht
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)


We introduce a probabilistic classifier that combines multiple instance learning and relational learning. While multiple instance learning allows automated cancer diagnosis from only image-level annotations, relational learning allows exploiting changes in cell formations due to cancer. Our method extends Gaussian process multiple instance learning with a relational likelihood that brings improved diagnostic performance on two tissue microarray data sets (breast and Barrett’s cancer) when similarity of cell layouts in different tissue regions is used as relational side information.


Receiver Operating Characteristic Curve Local Binary Pattern Side Information Marginal Likelihood Multiple Instance 
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.
    Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS (2003)Google Scholar
  2. 2.
    Ruifrok, A.C., et al.: Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol. 23, 291–299 (2001)Google Scholar
  3. 3.
    Sindhwani, W., et al.: Relational learning with Gaussian processes. In: NIPS (2007)Google Scholar
  4. 4.
    Xu, Y., et al.: Multiple clustered instance learning for histopathology cancer image classification, segmentation and clustering. In: CVPR (2012)Google Scholar
  5. 5.
    Gelasca, E.D., et al.: Evaluation and benchmark for biological image segmentation. In: ICIP (2008)Google Scholar
  6. 6.
    Getoor, L., Taskar, B.: Introduction to statistical relational learning. MIT Press (2007)Google Scholar
  7. 7.
    Kandemir, M., Feuchtinger, A., Walch, A., Hamprecht, F.A.: Digital Pathology: Multiple instance learning can detect Barrett’s cancer. In: ISBI (2014)Google Scholar
  8. 8.
    Kim, M., Torre, F.: Gaussian processes multiple instance learning. In: ICML (2010)Google Scholar
  9. 9.
    Maron, O., et al.: A framework for multiple-instance learning. In: NIPS (1998)Google Scholar
  10. 10.
    Silva, R., Chu, W., Ghahramani, Z.: Hidden common cause relations in relational learning. In: NIPS (2007)Google Scholar
  11. 11.
    Viola, P., et al.: Multiple instance boosting for object detection. In: NIPS (2005)Google Scholar
  12. 12.
    Zhang, D., Liu, Y., Si, L., Zhang, J., Lawrence, R.D.: Multiple instance learning on structured data. In: NIPS (2011)Google Scholar
  13. 13.
    Zhang, G., Yin, J., Li, Z., Su, X., Li, G., Zhang, H.: Automated skin biopsy histopathological image annotation using multi-instance representation and learning. BMC Medical Genomics 6(suppl. 3), S10 (2013)CrossRefGoogle Scholar
  14. 14.
    Zhang, Q., Goldman, S.A.: EM-DD: An improved multiple-instance learning technique. In: NIPS (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Melih Kandemir
    • 1
  • Chong Zhang
    • 2
  • Fred A. Hamprecht
    • 1
  1. 1.Heidelberg University HCI/IWRGermany
  2. 2.CellNetworksHeidelberg UniversityGermany

Personalised recommendations