Segmentation and mapping of highly convoluted contours with applications to medical images

A method that simultaneously identifies the central layer of the human cortex and maps it onto the interval [0,1] of the real axis is presented. Statistical and geometric information is incorporated into a global variational problem, whose solution is obtained iteratively. The method is evaluated on a set of magnetic resonance images, acquired with a protocol that optimizes the contrast between the cortical gray matter and the underlying white matter