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

In this paper, we propose a new knowledge-based method illustrated in the c ontext of segmentation, which labels internal brain structures viewed by ma gnetic resonance imaging (MRI). In order to improve the accuracy of the lab eling, we introduce a fuzzy model of regions of interest (ROI) by analogy w ith the electrostatic potential distribution, to represent more appropriate ly the knowledge of distance, shape and relationship of structures. The kno wledge is mainly derived from the Talairach stereotaxic atlas. The labeling is achieved by the regionwise labeling using genetic algorithms (GAs), fol lowed by a voxelwise amendment using parallel region growing. The fuzzy mod el is used both to design the fitness function of GAs, and to guide the reg ion growing. The performance of our proposed method has been quantitatively validated by six indices with respect to manually labeled images. (C) 2001 Elsevier Science B.V. All rights reserved.