Representation Learning: A Unified Deep Learning Framework for Automatic Prostate MR Segmentation

  • Shu Liao
  • Yaozong Gao
  • Aytekin Oto
  • Dinggang Shen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8150)


Image representation plays an important role in medical image analysis. The key to the success of different medical image analysis algorithms is heavily dependent on how we represent the input data, namely features used to characterize the input image. In the literature, feature engineering remains as an active research topic, and many novel hand-crafted features are designed such as Haar wavelet, histogram of oriented gradient, and local binary patterns. However, such features are not designed with the guidance of the underlying dataset at hand. To this end, we argue that the most effective features should be designed in a learning based manner, namely representation learning, which can be adapted to different patient datasets at hand. In this paper, we introduce a deep learning framework to achieve this goal. Specifically, a stacked independent subspace analysis (ISA) network is adopted to learn the most effective features in a hierarchical and unsupervised manner. The learnt features are adapted to the dataset at hand and encode high level semantic anatomical information. The proposed method is evaluated on the application of automatic prostate MR segmentation. Experimental results show that significant segmentation accuracy improvement can be achieved by the proposed deep learning method compared to other state-of-the-art segmentation approaches.


  1. 1.
    Shen, D., Davatzikos, C.: HAMMER: Hierarchical attribute matching mechanism for elastic registration. IEEE TMI 21, 1421–1439 (2002)Google Scholar
  2. 2.
    Guo, Y., Zhao, G., Pietikainen, M.: Discriminative features for texture description. Pattern Recognition 45, 3834–3843 (2012)CrossRefGoogle Scholar
  3. 3.
    Mallat, G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE PAMI 11, 674–693 (1989)CrossRefzbMATHGoogle Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  5. 5.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layerwise training of deep networks. In: NIPS, pp. 153–160 (2006)Google Scholar
  6. 6.
    Hinton, G., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neu. Comp., 1527–1554 (2006)Google Scholar
  7. 7.
    Le, Q., Zou, W., Yeung, S., Ng, A.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: CVPR, pp. 3361–3368 (2011)Google Scholar
  8. 8.
    Hyvarinen, A., Hurri, J., Hoyer, P.: Natural Image Statistics. Springer (2009)Google Scholar
  9. 9.
    Rousseau, F., Habas, P., Studholme, C.: A supervised patch-based approach for human brain labeling. IEEE TMI 30, 1852–1862 (2011)Google Scholar
  10. 10.
    Coupe, P., Manjon, J., Fonov, V., Pruessner, J., Robles, M., Collins, D.: Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation. NeuroImage 54, 940–954 (2011)CrossRefGoogle Scholar
  11. 11.
    Zhang, S., Zhan, Y., Dewan, M., Huang, J., Metaxas, D., Zhou, X.: Towards robust and effective shape modeling: sparse shape composition. MedIA 16, 265–277 (2012)Google Scholar
  12. 12.
    Klein, S., Heide, U., Lips, I., Vulpen, M., Staring, M., Pluim, J.: Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Medical Physics 35, 1407–1417 (2008)CrossRefGoogle Scholar
  13. 13.
    Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE PAMI 24, 971–987 (2002)CrossRefGoogle Scholar
  14. 14.
    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

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Shu Liao
    • 1
  • Yaozong Gao
    • 1
  • Aytekin Oto
    • 2
  • Dinggang Shen
    • 1
  1. 1.Department of Radiology and BRICUniversity of North Carolina at Chapel HillUSA
  2. 2.Department of Radiology, Section of UrologyUniversity of ChicagoUSA

Personalised recommendations