An Automatical Segmentation Method for Brain MR Images
Yunjie Chen, Zhenkai Wang, Byeungwoo Jeon, Jin Wang, Jeong-Uk Kim · Advanced science and technology letters · 2016
Brain magnetic resonance (MR) images have been widely used for analyzing brain diseases. However, due to the existence of noise and intensity inhomogeneity, many segmentation methods are hard to find accurate resuslts. This paper presents a novel variational framework for the registration, segmentation and bias estimation simultaneously. We first presented an improved segmentation model by using local region information, which can estimate the bias field meanwhile segmenting images. Then, we defined a coupled term to combine the segmentation and an improved registration method. The registration term can provide shape information as a prior to guide the segmentation and the segmentation term can provide the edge information to guide the registration. The segmentation results proved that the proposed method can obtain more accurate results.