A review of segmentation method for MR image

Abstract

Magnetic resonance (MR) is a typical medical imaging technique. It can provide high resolution 3D image with anatomical and function information through analyzing MRI sequence, which facilitates and improves diagnosis and patient treatment. The first important step in image analysis is image segmentation. In this paper, numerous methods that have been developed for segmentation in MRI are reviewed. We study these segmentation strategies and perform a qualitative discussion according to 3 categories, i.e. traditional image processing method, statistical-based segmentation method and partition technique with bias field estimation.