Deep Segmentation Refinement with Result-Dependent Learning
In this contribution, we propose a 2D deep segmentation refinement approach, that is inspired by the U-Net architecture and incorporates result-dependent loss adaptation. The performance of our method regarding segmentation quality is evaluated on the example of hip joint segmentation in T1-weighted MRI data sets. The results are compared to an ordinary U-Net implementation. While the segmentation quality of the proximal femur does not significantly change, our proposed method shows promising improvements for the segmentation of the pelvic bone complex, which shows more shape variability in the 2D image slices along the longitudinal axis.
Unable to display preview. Download preview PDF.
- 4.Klein A, Warszawski J, Hillengaß, et al. Towards whole-body CT bone segmentation. Proc BVM. 2018; p. 204–209.Google Scholar
- 5.Ronneberger O, Fischer P, Brox T; Springer. U-net: convolutional networks for biomedical image segmentation. Proc MICCAI. 2015; p. 234–241.Google Scholar
- 6.Ravishankar H, Venkataramani R, Thiruvenkadam S, et al.; Springer. Learning and incorporating shape models for semantic segmentation. Proc MICCAI. 2017; p. 203–211.Google Scholar
- 7.Newell A, Yang K, Deng J. Stacked hourglass networks for human pose estimation. Proc ECCV. 2016; p. 483–499.Google Scholar