Subject-Specific Cardiac Segmentation Based on Reinforcement Learning with Shape Instantiation

  • Lichao Wang
  • Su-Lin Lee
  • Robert Merrifield
  • Guang-Zhong Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)


Subject-specific segmentation for medical images plays a critical role in translating medical image computing techniques to routine clinical practice. Many current segmentation methods, however, are still focused on building general models, and thus lack the generalizability for unseen, particularly pathological data. In this paper, a reinforcement learning algorithm is proposed to integrate specific human expert behavior for segmenting subject-specific data. The algorithm uses a generic two-layer reinforcement learning framework and incorporates shape instantiation to constrain the target shape geometrically. The learning occurs in the background when the user segments the image in real-time, thus eliminating the need to prepare subject-specific training data. Detailed validation of the algorithm on hypertrophic cardiomyopathy (HCM) datasets demonstrates improved segmentation accuracy, reduced user-input, and thus the potential clinical value of the proposed algorithm.


Reinforcement Learning Hypertrophic Cardiomyopathy Active Contour Partial Little Square Regression Partial Little Square Regression Model 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing 7, 359–369 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Transactions on Image Processing 10, 266–277 (2001)CrossRefzbMATHGoogle Scholar
  3. 3.
    Cootes, T.F., Hill, A., Taylor, C.J., Haslam, J.: The Use of Active Shape Models for Locating Structures in Medical Images. In: Proceedings of the 13th International Conference on Information Processing in Medical Imaging, pp. 33–47. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  4. 4.
    Lekadir, K., Keenan, N.G., Pennell, D.J., Yang, G.-Z.: An Inter-Landmark Approach to 4-D Shape Extraction and Interpretation: Application to Myocardial Motion Assessment in MRI. IEEE Transactions on Medical Imaging 30, 52–68 (2011)CrossRefGoogle Scholar
  5. 5.
    Cecchi, F., Yacoub, M.H., Olivotto, I.: Hypertrophic cardiomyopathy in the community: why we should care. Nat. Clin. Pract. Cardiovasc. Med. 2, 324–325 (2005)CrossRefGoogle Scholar
  6. 6.
    Davatzikos, C., Tao, X., Shen, D.: Hierarchical active shape models, using the wavelet transform. IEEE Transactions on Medical Imaging 22, 414–423 (2003)CrossRefGoogle Scholar
  7. 7.
    Wang, Y., Staib, L.H.: Boundary finding with prior shape and smoothness models. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 738–743 (2000)CrossRefGoogle Scholar
  8. 8.
    de Bruijne, M., van Ginneken, B., Viergever, M.A., Niessen, W.J.: Interactive segmentation of abdominal aortic aneurysms in CTA images. Medical Image Analysis 8, 127–138 (2004)CrossRefGoogle Scholar
  9. 9.
    Hug, J., Brechbühler, C., Székely, G.: Model-Based Initialisation for Segmentation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 290–306. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Wang, L., Merrifield, R., Yang, G.-Z.: Reinforcement Learning for Context Aware Segmentation. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011, Part III. LNCS, vol. 6893, pp. 627–634. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Lee, S.-L., Chung, A., Lerotic, M., Hawkins, M.A., Tait, D., Yang, G.-Z.: Dynamic shape instantiation for intra-operative guidance. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010, Part I. LNCS, vol. 6361, pp. 69–76. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Matheron, G.: Principles of geostatistics. Economic Geology 58, 1246–1266 (1963)CrossRefGoogle Scholar
  13. 13.
    Lee, S.-L., Wu, Q., Huntbatch, A., Yang, G.-Z.: Predictive K-PLSR myocardial contractility modeling with phase contrast MR velocity mapping. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 866–873. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  14. 14.
    Ablitt, N.A., Jianxin, G., Keegan, J., Stegger, L., Firmin, D.N., Yang, G.-Z.: Predictive cardiac motion modeling and correction with partial least squares regression. IEEE Transactions on Medical Imaging 23, 1315–1324 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lichao Wang
    • 1
  • Su-Lin Lee
    • 1
  • Robert Merrifield
    • 1
  • Guang-Zhong Yang
    • 1
  1. 1.The Hamlyn Centre for Robotic SurgeryImperial College LondonUK

Personalised recommendations