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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
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.
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.
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.
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.
Davatzikos C, Xiaodong Tao, Dinggang Shen. Hierarchical active shape models, using the wavelet transform. IEEE Trans Med Imaging. 2003 Mar;22(3):414-423.
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.
Kingma DP, Welling M. Auto-encoding variational bayes. In: Proc. ICLR; 2014. p. 1-14.
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.
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.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Uzunova, H., Kaftan, P., Wilms, M., Forkert, N.D., Handels, H., Ehrhardt, J. (2020). Quantitative Comparison of Generative Shape Models for Medical Images. In: Tolxdorff, T., Deserno, T., Handels, H., Maier, A., Maier-Hein, K., Palm, C. (eds) Bildverarbeitung für die Medizin 2020. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-29267-6_45
Download citation
DOI: https://doi.org/10.1007/978-3-658-29267-6_45
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-29266-9
Online ISBN: 978-3-658-29267-6
eBook Packages: Computer Science and Engineering (German Language)