An Improved BET Method for Brain Segmentation

Abstract

The Brain Extraction Tool (BET) developed by Smith is widely used for brain segmentation due to its simplicity, accuracy and insensitivity to parameter settings. However, it typically requires a large number of iterations to generate acceptable results. It also sometimes fails to recognize boundaries of the brain. Moreover, obvious under-segmentation occurs for some datasets. In this paper, we present an improved BET method where at each iteration, we enhance the vertex displacement, add a new search path and embed an independent surface reconstruction process. These strategies lead to much faster convergence. Furthermore, a scheme based on fuzzy c-means is proposed to refine the segmentation. Experimental results based on various datsets demonstrated that the proposed method significantly outperforms the original BET and other competing methods.