Adaptive Confidence Regions of Motion Predictions from Population Exemplar Models

  • Golnoosh Samei
  • Grzegorz Chlebus
  • Gabor Székely
  • Christine Tanner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8198)


Precise radiation therapies require not only accurate prediction of the motion of the structures in the treatment region, but also confidence values of these predictions to enable planning of residual motion and detection of failure predictions. While various motion models have been proposed for the prediction of motion in the abdomen due to free-breathing, none has provided confidence regions. In this study we use the conditional probability density function of statistical liver motion models for predicting confidence regions, propose a method for optimizing the accuracy of the confidence regions and show the adaptability of the confidence regions due to partial observations when using exemplar models. The average accuracy of the confidence regions of single Gaussian (SG) models could be improved to the level of the exemplar models. Exemplar models provided on average better motion predictions (1.14 mm) and slightly smaller 68% confidence regions (1.36 mm) than the SG models (1.21 mm, 1.43 mm resp.). The confidence region size correlated temporally on average weakly (r=0.35) with the errors of the motion prediction for the exemplar models, leading to a higher percentage of treatable locations and lower motion prediction errors per duty cycle than SG models.


Statistical population model motion prediction confidence regions exemplar models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Tanner, C., Boye, D., Samei, G., Székely, G.: Review on 4D models for organ motion compensation. Critical Reviews in Biomedical Engineering 40(2), 135 (2012)CrossRefGoogle Scholar
  2. 2.
    McClelland, J., Hawkes, D., Schaeffter, T., King, A.: Respiratory motion models: A review. Medical Image Analysis 17, 19–42 (2012)CrossRefGoogle Scholar
  3. 3.
    Van Herk, M.: Errors and margins in radiotherapy. In: Seminars in Radiation Oncology, vol. 14, pp. 52–64. Elsevier (2004)Google Scholar
  4. 4.
    Blake, A., Isard, M.: Active contours (1998)Google Scholar
  5. 5.
    Blanc, R., Syrkina, E., Székely, G.: Estimating the confidence of statistical model based shape prediction. In: Prince, J.L., Pham, D.L., Myers, K.J. (eds.) IPMI 2009. LNCS, vol. 5636, pp. 602–613. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Bishop, C.M.: Pattern recognition and machine learning, vol. 1. Springer, New York (2006)zbMATHGoogle Scholar
  7. 7.
    Baka, N., de Bruijne, M., Reiber, J., Niessen, W., Lelieveldt, B.: Confidence of model based shape reconstruction from sparse data. In: Int. Symposium on Biomedical Imaging: From Nano to Macro, pp. 1077–1080. IEEE (2010)Google Scholar
  8. 8.
    Samei, G., Tanner, C., Székely, G.: Predicting liver motion using exemplar models. In: Yoshida, H., Hawkes, D., Vannier, M.W. (eds.) Abdominal Imaging 2012. LNCS, vol. 7601, pp. 147–157. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    von Siebenthal, M., Székely, G., Lomax, A., Cattin, P.C.: Inter-subject modelling of liver deformation during radiation therapy. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 659–666. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  10. 10.
    Ahrendt, P.: The multivariate gaussian probability distribution. Tech. rep. (2005)Google Scholar
  11. 11.
    Dudani, S.A.: The distance-weighted k-nearest-neighbor rule. Transactions on Systems, Man and Cybernetics (4), 325–327 (1976)Google Scholar
  12. 12.
    Van Herk, M., Remeijer, P., Rasch, C., Lebesque, J.V.: The probability of correct target dosage: dose-population histograms for deriving treatment margins in radiotherapy. Int. J. Radiat. Oncol. Boil. Phys. 47(4), 1121 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Golnoosh Samei
    • 1
  • Grzegorz Chlebus
    • 2
  • Gabor Székely
    • 1
  • Christine Tanner
    • 1
  1. 1.Computer Vision LaboratoryETH ZurichZurichSwitzerland
  2. 2.Faculty of ElectronicsWroclaw University of TechnologyWroclawPoland

Personalised recommendations