A Novel Multi-Atlas and Multi-Channel (MAMC) Approach for Multiple Sclerosis Lesion Segmentation in Brain MRI
Changjun Hu, Liansong Song, Meiru Liu, Jingjing Wang, Liren Zhang · 2018
This paper presents a novel approach for automatic segmentation of MS lesion in brain MR image. The first research focus is using the minimum of the MR image energy function to do the bias field correction and the normal tissue segmentation simultaneously. The second research focus is the development of a multi-atlas and multi-channel (MAMC) approach for the segmentation of MS lesion from the grey matter region in T1-w atlas as well as from the white matter region in FLAIR atlas. The last research focus is the multiple-atlas based label fusion using local weighted voting strategy, in which a specific coefficient as the weight is assigned to each individual atlas being involved in the label fusion. The coefficient is obtained based on the maximum likelihood function between atlas and the target image.