A Bayesian model of shape and appearance for subcortical brain segmentation

► Automated segmentation of 15 subcortical structures with full Bayesian formulation. ► Vertex-analysis for detecting local geometric changes with no arbitrary smoothing. ► Good performance over a wide range of demographics and T1-weighted images. ► Avoids arbitrary scaling parameters and ill-conditioning in usual appearance models. ► Freely available as part of FSL - tool is called FIRST.