Graph-based optimal multi-surface segmentation with a star-shaped prior: Application to the segmentation of the optic disc and cup

@article{Bai2014GraphbasedOM,
  title={Graph-based optimal multi-surface segmentation with a star-shaped prior: Application to the segmentation of the optic disc and cup},
  author={Junjie Bai and Mohammad Saleh Miri and Yinxiao Liu and P. K. Saha and M. Garvin and X. Wu},
  journal={2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)},
  year={2014},
  pages={525-528}
}
  • Junjie Bai, Mohammad Saleh Miri, +3 authors X. Wu
  • Published 2014
  • Computer Science
  • 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)
  • A novel graph-based optimal segmentation method which can simultaneously segment multiple star-shaped surfaces is presented in this paper. Minimum and maximum surface distance constraints can be enforced between different surfaces. In addition, the segmented surfaces are ensured to be smooth by incorporating surface smoothness constraints which limit the variation between adjacent surface voxels. A consistent digital ray system is utilized to make sure the segmentation result is star-shaped and… CONTINUE READING
    Incorporating prior knowledge in medical image segmentation: a survey
    • 18
    • PDF
    Optimal Multi-Object Segmentation with Novel Gradient Vector Flow Based Shape Priors
    • 3
    • PDF
    Segmentation of optic nerve head images
    • 1
    Efficient optimization for labeling problems with prior information: applications to natural and medical images

    References

    Publications referenced by this paper.
    SHOWING 1-8 OF 8 REFERENCES
    Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach
    • 613
    • PDF
    Graph Cuts and Efficient N-D Image Segmentation
    • 1,941
    • PDF
    Star Shape Prior for Graph-Cut Image Segmentation
    • 295
    • PDF
    Simultaneous searching of globally optimal interacting surfaces with shape priors
    • 41
    Globally optimal segmentation of multi-region objects
    • 150
    • PDF
    Consistent Digital Rays
    • 13
    • Highly Influential