A 3-D deformable surface method for automatic hippocampus-amygdala complex segmentation

In this paper, we propose an atlas-based method for hippocampus-amygdala complex segmentation. An atlas is registered on all subjects and its transformation is calculated for each subject. This transformation is applied to the structural segmentation of the complex in atlas to construct an initial surface for the hippocampus-amygdala complex of each subject. A possibility approach is introduced for the segmentation process. Two different kinds of deformation based on edges and information obtained from tissue segmentation are used to find different parts of the complex. A new energy is defined to use tissue information. This energy is adopted to expand the model to embed dominant gray matter points in the volume and also withdraw from dominant white matter and CSF points. The initial shape is divided into several parts. In the normal direction of the center of each part, we construct a profile which search for the best point that maximizes this new energy. This algorithm is reliable for finding the overall shape of the complex. It overcomes the poor features of the complex such as weak edges and noise. The algorithm is examined on 5 different subjects and validated using two different validation methods.