Automatic Active Contours Propagation in a Sequence of Medical Images

Abstract

Received Revised AcceptedIn this paper we present a new algorithm to track an organ in a sequence of medical images in order to achieve a 3D reconstruction. The automatic method that we propose allows the tracking of the external contour of the anatomical organ in all the sequence from one contour initialized by the user on the first image. The required operations for our tracking method are the region-based active contours segmentation. The objects localization with dynamic prediction of displacements is based on the level-set functions and the definition of the region of interest for the robust local estimation of the image model. An application of this method is the 3D reconstruction of abdominal aorta.

Variational approximation of a constraint signal by a Mumford-Shah type energy functional

“…Actually, the used filters in line and column could be considered as the projections of a given two dimensional vector field on the picture. In perspective of this work, we are planning to compare our method with level set methods [7].…”

3D Image Modelling and Specific Treatments in Orthodontics Domain

“…In the first level, in a 2D field, several separation methods were developed to deal with the management of topology. The majority of these methods are based on deformable models where the changes of topology are managed implicitly using the level set formulation (Malladi et al 1995;Djemal et al 2006). Others tried to solve this problem by the definition of topological operators adapted to the studied structure (Rey et al 1999), but it is difficult to generalize them; therefore, results can be obtained only on synthetic models.…”

Automatic segmentation in image stacks based on multi-constraint level-set evolution

“…This method usually applies gradient vector field [12] but it does not permit the split of topology. (iii) Contour inheriting method [13,14]. Previous contours or their deformations are used as initial contours, which makes it difficult to segment joints due to disturbance of other tissues.…”

“…We compare automation degree and accuracy between our algorithm and Djemal, et al's algorithm [14]. The essence of Djemal, et al's algorithm is to predict k C according to…”