Detection of the carpal bone contours from 3-D MR images of the wrist using a planar radial scale-space snake

In this paper we consider the problems encountered when applying snake mode ls to detect the contours of the carpal bones in 3-D MR images of the wrist , In order to improve the performance of the original snake model introduce d by Kass [1], we propose a new image force based on one-dimensional (1-D) second-order Gaussian filtering and contrast equalization, The improved snake is less sensitive to model initialization and has no ten dency to cut off contour sections of high curvature, because 1-D radial sca le-space relaxation is used, Contour orientation is used to minimize the in fluence of neighboring image structures. Due to 1-D contrast equalization a n intensity insensitive measure of external energy is obtained. As a conseq uence a good balance between internal and external energetic contributions of the snake is established, which also improves convergence. By incorporating this new image force into the snake model, we succeed in a ccurate contour detection, even when relatively high noise levels are prese nt and when the contrast varies along the contours of the bones.