• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Lymph node segmentation in CT slices using dynamic programming
 
  • Details
  • Full
Options
2011
  • Konferenzbeitrag

Titel

Lymph node segmentation in CT slices using dynamic programming

Abstract
An automatically extracted 2d contour of a lymph node in a single CT slice is required for size assessment as well as for the initialization of model based 3d lymph node segmentation algorithms. This paper presents a novel single slice lymph node segmentation approach. It finds a closed path around a seed point thereby minimizing an energy function which depends on gradients, intensities and shape priors. A globally optimal solution is guaranteed to be found using dynamic programming. The approach is evaluated on a set of 49 representative lymph nodes from clinical images for which manual expert segmentation is available. The resulting average dice similarity coefficient of 0.81 is close to manual segmentation (0.89).
Author(s)
Steger, Sebastian
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Ebert, Daniel
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Erdt, Marius
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Hauptwerk
IEEE International Symposium on Biomedical Imaging. From Nano to Macro, ISBI 2011
Konferenz
International Symposium on Biomedical Imaging (ISBI) 2011
Thumbnail Image
DOI
10.1109/ISBI.2011.5872801
Language
Englisch
google-scholar
IGD
Tags
  • dynamic programming

  • medical image process...

  • segmentation

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022