Geodesic regression of image and shape data for improved modeling of 4D trajectories

James Fishbaugh (1) , Marcel Prastawa (1) , Guido Gerig (1) , Stanley Durrleman (2)

1 SCI Institute - Scientific Computing and Imaging Institute
2 ARAMIS - Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris]

A variety of regression schemes have been proposed on im-ages 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 pa-rameterization of deformations, where the dimensionality of the deformation is determined by the complexity of anatom-ical changes in time rather than the sampling of the image and/or the geometric data. We derive a gradient descent al-gorithm which simultaneously estimates baseline images and shapes, location of control points, and momenta. Experi-ments on real medical data demonstrate that our framework effectively combines image and shape information, resulting in improved modeling of 4D (3D space + time) trajectories.

Domaines: Imagerie médicale; Algorithme et structure de données [cs.DS]

James Fishbaugh, Marcel Prastawa, Guido Gerig, Stanley Durrleman. Geodesic regression of image and shape data for improved modeling of 4D trajectories. ISBI 2014 - 11th International Symposium on Biomedical Imaging, Apr 2014, Beijin, China. pp.385 - 388, ⟨10.1109/ISBI.2014.6867889⟩. ⟨hal-01108243⟩