A Level Set Bridging Force for the Segmentation of Dendritic Spines

The paper focusses on a group of segmentation problems dealing with 3D data sets showing thin objects that appear disconnected in the data due to partial volume effects or a large spacing between neighbouring slices. We propose a modification of the speed function for the well-known level set method to bridge these discontinuities. This allows for the segmentation of the object as a whole. In this paper we are concerned with treelike structures, particularly dendrites in microscopic data sets, whose shape is unknown prior to segmentation. Using the modified speed function, our algorithm segments dendrites and their spines, even if parts of the object appear to be disconnected due to artifacts. 1 Motivation A number of problems arise when an object in a 3D data set should be segmented. Depending on the modality there may be certain artifacts, e.g. magnetic field inhomogeneities in MR-images or metal artifacts in CT-images. An artifact common to almost all image acquisition technique...

• Type: Conference
• Year: 2007
• Where: CAIP
• Authors: Karsten Rink, Klaus D. Tönnies
• Keywords: CAIP 2007, Data Set, Partial Volume Effect, Speed Function