Live-wire-based segmentation using similarities between corresponding image structures

Matthias Färber*, Jan Ehrhardt, Heinz Handels

*Corresponding author for this work
15 Citations (Scopus)

Abstract

A live-wire-based segmentation method that exploits similarities of corresponding object contours is presented. The method accelerates the segmentation process transferring anchor points of segmented reference contours to unsegmented target slices automatically. The target contours are created using the live-wire algorithm trained by features of the reference contours. An automatic contour correction improves the segmentation. Only few user interactions with an intuitive contour editor are necessary. The evaluation using intra- and interpatient transfer shows that 51-73% of interaction time can be saved compared to normal live-wire preserving the segmentation quality.

Original languageEnglish
JournalComputerized Medical Imaging and Graphics
Volume31
Issue number7
Pages (from-to)549-560
Number of pages12
ISSN0895-6111
DOIs
Publication statusPublished - 01.10.2007

Cite this