Quantitative comparison of generative shape models for medical images

Hristina Uzunova*, Paul Kaftan, Matthias Wilms, Nils D. Forkert, Heinz Handels, Jan Ehrhardt

*Corresponding author for this work


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.

Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2020
EditorsThomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Andreas Maier, Klaus H. Maier-Hein, Christoph Palm
Number of pages7
PublisherSpringer Vieweg, Wiesbaden
Publication date12.02.2020
ISBN (Print)978-3-658-29266-9
ISBN (Electronic)978-3-658-29267-6
Publication statusPublished - 12.02.2020
EventBildverarbeitung für die Medizin 2020 - International workshop on Algorithmen - Systeme - Anwendungen
- Berlin, Germany
Duration: 15.03.202017.03.2020
Conference number: 237969


Dive into the research topics of 'Quantitative comparison of generative shape models for medical images'. Together they form a unique fingerprint.

Cite this