Segmentation of magnetic resonance images of brain and abdomen

Abstract

Segmentation of MRI data is required for many applications, such as the comparison of different structures or time points, and for annotation purposes. Manual segmentation requires high-level expertise and is subject to inter- and intra- observer variability, time and labor consuming. All these urge the need for automatic segmentation algorithms. In this work we try to address two segmentation problems in MR imaging and design automatic algorithms to solve them.