Geodesic shape regression in the framework of currents

Update item information
Publication Type pre-print
School or College <blank>
Department <blank>
Creator Gerig, Guido
Other Author Fishbaugh, James; Prastawa, Marcel; Durrleman, Stanley
Title Geodesic shape regression in the framework of currents
Date 2013-01-01
Description Shape regression is emerging as an important tool for the statistical analysis of time dependent shapes. In this paper, we develop a new generative model which describes shape change over time, by extending simple linear regression to the space of shapes represented as currents in the large deformation diffeomorphic metric mapping (LDDMM) framework. By analogy with linear regression, we estimate a baseline shape (intercept) and initial momenta (slope) which fully parameterize the geodesic shape evolution. This is in contrast to previous shape regression methods which assume the baseline shape is fixed. We further leverage a control point formulation, which provides a discrete and low di- mensional parameterization of large diffeomorphic transformations. This flexible system decouples the parameterization of deformations from the specific shape representation, allowing the user to define the dimensionality of the deformation parameters. We present an optimization scheme that estimates the baseline shape, location of the control points, and initial momenta simultaneously via a single gradient descent algorithm. Finally, we demonstrate our proposed method on synthetic data as well as real anatomical shape complexes.
Type Text
Publisher Springer
Volume 7917
First Page 718
Last Page 729
Language eng
Bibliographic Citation Fishbaugh, J., Prastawa, M., Gerig, G., & Durrleman, S. (2013). Geodesic shape regression in the framework of currents. Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI), 7917, 718-29.
Rights Management (c) Springer (The original publication is available at ; The final publication is available at Springer via
Format Medium application/pdf
Format Extent 1,566,974 bytes
Identifier uspace,18997
ARK ark:/87278/s6rz2n69
Setname ir_uspace
Date Created 2014-11-06
Date Modified 2021-05-06
ID 712713
Reference URL
Back to Search Results