Sciweavers

Share
ICIP
2008
IEEE

Reference-based probabilistic segmentation as non-rigid registration using Thin Plate Splines

9 years 4 months ago
Reference-based probabilistic segmentation as non-rigid registration using Thin Plate Splines
In this paper we demonstrate the effectiveness of reference (or atlas)-based non-rigid registration to the segmentation of medical and biological imagery. In particular we introduce a segmentation functional exploiting feature information about the reference image and we minimize it with respect to the parameters of the non-rigid transformation, akin to a regionbased maximum likelihood estimation process. The warping transformation is modeled using Thin Plate Splines, which incorporate information about the global rigid motion and the non-rigid local displacements. Extensive experimental evaluations and comparisons with other segmentation techniques on a complex biological dataset are presented. The proposed algorithm outperforms the others in both classification rate and, in particular, localization accuracy.
Luca Bertelli, Pratim Ghosh, B. S. Manjunath, Fr&e
Added 20 Oct 2009
Updated 27 Oct 2009
Type Conference
Year 2008
Where ICIP
Authors Luca Bertelli, Pratim Ghosh, B. S. Manjunath, Frédéric Gibou
Comments (0)
books