Knowledge-based segmentation and labeling of brain structures from MRI images

8 In this paper, we propose a new knowledge-based method illustrated in the context of segmentation, which labels 9 internal brain structures viewed by magnetic resonance imaging (MRI). In order to improve the accuracy of the la10 beling, we introduce a fuzzy model of regions of interest (ROI) by analogy with the electrostatic potential distribution, 11 to represent more appropriately the knowledge of distance, shape and relationship of structures. The knowledge is 12 mainly derived from the Talairach stereotaxic atlas. The labeling is achieved by the regionwise labeling using genetic 13 algorithms (GAs), followed by a voxelwise amendment using parallel region growing. The fuzzy model is used both to 14 design the ®tness function of GAs, and to guide the region growing. The performance of our proposed method has been 15 quantitatively validated by six indices with respect to manually labeled images. Ó 2001 Elsevier Science B.V. All rights 16 reserved.