TY - GEN
T1 - Geodesic regression of image and shape data for improved modeling of 4D trajectories
AU - Fishbaugh, James
AU - Prastawa, Marcel
AU - Gerig, Guido
AU - Durrleman, Stanley
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/7/29
Y1 - 2014/7/29
N2 - A variety of regression schemes have been proposed on images or shapes, although available methods do not handle them jointly. In this paper, we present a framework for joint image and shape regression which incorporates images as well as anatomical shape information in a consistent manner. Evolution is described by a generative model that is the analog of linear regression, which is fully characterized by baseline images and shapes (intercept) and initial momenta vectors (slope). Further, our framework adopts a control point parameterization of deformations, where the dimensionality of the deformation is determined by the complexity of anatomical changes in time rather than the sampling of the image and/or the geometric data. We derive a gradient descent algorithm which simultaneously estimates baseline images and shapes, location of control points, and momenta. Experiments on real medical data demonstrate that our framework effectively combines image and shape information, resulting in improved modeling of 4D (3D space + time) trajectories.
AB - A variety of regression schemes have been proposed on images or shapes, although available methods do not handle them jointly. In this paper, we present a framework for joint image and shape regression which incorporates images as well as anatomical shape information in a consistent manner. Evolution is described by a generative model that is the analog of linear regression, which is fully characterized by baseline images and shapes (intercept) and initial momenta vectors (slope). Further, our framework adopts a control point parameterization of deformations, where the dimensionality of the deformation is determined by the complexity of anatomical changes in time rather than the sampling of the image and/or the geometric data. We derive a gradient descent algorithm which simultaneously estimates baseline images and shapes, location of control points, and momenta. Experiments on real medical data demonstrate that our framework effectively combines image and shape information, resulting in improved modeling of 4D (3D space + time) trajectories.
UR - http://www.scopus.com/inward/record.url?scp=84927942663&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84927942663&partnerID=8YFLogxK
U2 - 10.1109/isbi.2014.6867889
DO - 10.1109/isbi.2014.6867889
M3 - Conference contribution
AN - SCOPUS:84927942663
T3 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
SP - 385
EP - 388
BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
Y2 - 29 April 2014 through 2 May 2014
ER -