Reference-based Probabilistic Segmentation as Non-Rigid Registration using Thin Plate Splines

Luca Bertelli, Pratim Ghosh, B. S. Manjunath
Electrical and Computer Engineering Department
University of California, Santa Barbara
93106 Santa Barbara, CA
{lbertelli, pratim, manj} [at] ece.ucsb.edu

Frederic Gibou
Mechanical Engineering Department
University of California, Santa Barbara
93106 Santa Barbara, CA
gibou [at] engineering.ucsb.edu

Abstract

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 region based 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.
[PDF] [BibTex]
Luca Bertelli, Pratim Ghosh, B. S. Manjunath, Frederic Gibou,
Proc. IEEE International Conference on Image Processing, pp. 3052-3055, San Diego, CA, Oct. 2008.
Node ID: 505 , DB ID: 312 , Lab: VRL , Target: Conference
Subject: [Detection on Images and Videos] « Look up more