Automatic segmentation of deep brain structures in MR images has attracted considerable scientific attention due to the widespread use of MRI and to the principal role of some structures in various mental disorders. More specifically, morphological analysis of the hippocampus (HC) and amygdala (AG) is considered a key requirement for the assessment, treatment and follow-up of various mental disorders, including Major Depressive Disorder (MDD), Post-Traumatic Stress Disorder (PTSD), schizophrenia (SD), Alzheimer’s Disease, Bipolar disorder (BD), etc. In the literature, there exist a substantial amount of work relying on deformable models incorporating prior knowledge about structures’ anatomy and shape information. However, shape priors capture global shape characteristics and thus fail to model boundaries of varying properties; hippocampus’ boundaries present rich, poor and missing gradient regions. On top of that, shape prior knowledge is blended with image information in the evolution process, through global weighting of the two terms, again neglecting the spatially varying boundary properties, causing segmentation faults. Our work aims to achieve highly accurate HC and AG segmentation in MR images, based on the modeling of boundary properties at each anatomical location and the inclusion of appropriate image information for each of those. Hence, blending of image information and prior knowledge is based on a local weighting map, which mixes gradient information, regional and whole brain statistical information with a multi-atlas based spatial distribution map of the structure’s labels.