Advertisement

Quantitative Comparison of Generative Shape Models for Medical Images

  • Hristina UzunovaEmail author
  • Paul Kaftan
  • Matthias Wilms
  • Nils D. Forkert
  • Heinz Handels
  • Jan Ehrhardt
Conference paper
  • 58 Downloads
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Generative shape models play an important role in medical image analysis. Conventional methods like PCA-based statistical shape models (SSMs) and their various extensions have shown great success modeling natural shape variations in medical images, despite their limitations. Corresponding deep learning-based methods like (variational) autoencoders are well known to overcome many of those limitations. In this work, we compare two conventional and two deep learning-based generative shape modeling approaches to shed light on their limitations and advantages. Experiments on a publicly available 2D chest X-ray data set show that the deep learning methods achieve better specificity and generalization abilities for large training set sizes. However, for smaller training sets, the conventional SSMs are more robust and their latent space is more compact and easier to interpret.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Wilms M, Ehrhardt J, Handels H. A 4D statistical shape model for automated segmentation of lungs with large tumors. In: Proc. MICCAI 2012. Springer; 2012. p. 347–354.Google Scholar
  2. 2.
    Uzunova H, Wilms M, Handels H, et al. Training CNNs for image registration from few samples with model-based data augmentation. In: Proc. MICCAI 2017. Springer; 2017. p. 223–231.Google Scholar
  3. 3.
    Cootes TF, Taylor CJ, Cooper DH, et al. Active shape models & their training and application. Comput Vis Image Underst. 1995 Jan;61(1):38–59.Google Scholar
  4. 4.
    Kirschner M, Becker M, Wesarg S. 3D active shape model segmentation with non-linear shape priors. In: Proc. MICCAI 2011. Springer; 2011. p. 492–499.Google Scholar
  5. 5.
    Davatzikos C, Xiaodong Tao, Dinggang Shen. Hierarchical active shape models, using the wavelet transform. IEEE Trans Med Imaging. 2003 Mar;22(3):414-423.Google Scholar
  6. 6.
    Wilms M, Handels H, Ehrhardt J. Multi-resolution multi-object statistical shape models based on the locality assumption. Med Image Anal. 2017 May;38:17-29.Google Scholar
  7. 7.
    Kingma DP, Welling M. Auto-encoding variational bayes. In: Proc. ICLR; 2014. p. 1-14.Google Scholar
  8. 8.
    van Ginneken B, Stegmann MB, Loog M. Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med Image Anal. 2006;10(1):19-40.Google Scholar
  9. 9.
    Davies RH, Twining CJ, Cootes TF, et al. A minimum description length approach to statistical shape modeling. IEEE Trans Med Imaging. 2002 May;21(5):525-537.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  1. 1.Institute of Medical InformaticsUniversity of LübeckLübeckDeutschland
  2. 2.Department of RadiologyUniversity of CalgaryCalgaryKanada

Personalised recommendations