GAS: a Genetic Atlas Selection Strategy in Multi-Atlas Segmentation Framework

Multi-Atlas based Segmentation (MAS) algorithms have been successfully applied to a wide range of medical image segmentation tasks (Isgum et  al., 2009; Cardoso et al., 2013; Aljabar et al., 2009). Their success relies on the introduction of a priori knowledge using a set of pre-segmented images. An atlas consists of a medical image and a corresponding segmented label image. According to the subdivision proposed in Iglesias and Sabunc u (2014), a MAS algorithm can be implemented following four sequential steps: first each atlas image is registered to the target image (registration step), second either all or a subset of atlases are chosen (atlas selection step) and their label images are propagated into the target space (label pr opagation step).

Source: Medical Image Analysis - November 19, 2018 Category: Radiology Authors: Michela Antonelli, M. Jorge Cardoso, Edward W. Johnston, Mrishta Brizmohun Appayya, Benoit Presles, Marc Modat, Shonit Punwani, Sebastien Ourselin Source Type: research