Xl. Zeng et al., Segmentation and measurement of the cortex from 3-D MR images using coupled-surfaces propagation, IEEE MED IM, 18(10), 1999, pp. 927-937
Citations number
42
Categorie Soggetti
Radiology ,Nuclear Medicine & Imaging","Eletrical & Eletronics Engineeing
The cortex is the outermost thin layer of gray matter in the brain; geometr
ic measurement of the cortex helps in understanding brain anatomy and funct
ion. In the quantitative analysis of the cortex from MR images, extracting
the structure and obtaining a representation for various measurements are k
ey steps. While manual segmentation is tedious and labor intensive, automat
ic reliable efficient segmentation and measurement of the cortex remain cha
llenging problems, due to its convoluted nature. Here we present a new appr
oach of coupled-surfaces propagation, using level set methods to address su
ch problems, Our method is motivated by the nearly constant thickness of th
e cortical mantle and takes this tight coupling as an important constraint.
By evolving two embedded surfaces simultaneously, each driven by its own i
mage-derived information while maintaining the coupling, a final representa
tion of the cortical bounding surfaces and an automatic segmentation of the
cortex are achieved. Characteristics of the cortex, such as cortical surfa
ce area, surface curvature, and cortical thickness, are then evaluated, The
level set implementation of surface propagation offers the advantage of ea
sy initialization, computational efficiency, and the ability to capture dee
p sulcal folds. Results and validation from various experiments on both sim
ulated and real three-dimensional (3-D) MR images are provided.