Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Journal Article

Domain-specific cues improve robustness of deep learning-based segmentation of CT volumes


Scherf,  Nico
Institute for Medical Informatics and Biometry, University Hospital Carl Gustav Carus, Dresden, Germany;
Department Neurophysics (Weiskopf), MPI for Human Cognitive and Brain Sciences, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

(Publisher version), 2MB

Supplementary Material (public)
There is no public supplementary material available

Kloenne, M., Niehaus, S., Lampe, L., Merola, A., Reinelt, J., Roeder, I., et al. (2020). Domain-specific cues improve robustness of deep learning-based segmentation of CT volumes. Scientific Reports, 10(1): 10712. doi:10.1038/s41598-020-67544-y.

Cite as: https://hdl.handle.net/21.11116/0000-0006-D55D-2
Machine learning has considerably improved medical image analysis in the past years. Although data-driven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes. In this paper, we address these issues with a framework that adds domain-specific data preprocessing and augmentation to state-of-the-art CNN architectures. Our major focus is to stabilise the prediction performance over samples as a mandatory requirement for use in automated and semi-automated workflows in the clinical environment. To validate the architecture-independent effects of our approach we compare a neural architecture based on dilated convolutions for parallel multi-scale processing (a modified Mixed-Scale Dense Network: MS-D Net) to traditional scaling operations (a modified U-Net). Finally, we show that an ensemble model combines the strengths across different individual methods. Our framework is simple to implement into existing deep learning pipelines for CT analysis. It performs well on a range of tasks such as liver and kidney segmentation, without significant differences in prediction performance on strongly differing volume sizes and varying slice thickness. Thus our framework is an essential step towards performing robust segmentation of unknown real-world samples.