No abstract

No abstract

Abstract. We propose a new algorithm to find the corpus callosum automatically from midsagittal brain MR (magnetic resonance) images using the statistical characteristics and shape information of the corpus callosum. We first extract regions satisfying the statistical characteristics (gray level distributions) of the corpus callosum that have relatively high intensity values. Then we try to find a region matching the shape information of the corpus callosum. In order to match the shape information, we propose a new directed window region growing algorithm instead of using conventional contour matching. An innovative feature of the algorithm is that we adaptively relax the statistical requirement until we find a region matching the shape information. After the initial segmentation, a directed border path pruning algorithm is proposed in order to remove some undesired artifacts, especially on the top of the corpus callosum. The proposed algorithm was applied to over 120 images and provided promising results.

In this paper, we present an automated segmentation algorithm for three-dimensional sagittal brain MR images. We start the segmentation from a midsagittal brain MR image utilizing some landmarks, anatomical information and a connectivity-based threshold segmentation algorithm.Since the brain in adjacent slices has a similar size and shape, we propose to use the segmentation result of the midsagittal brain MR image as a mask to guide segmentation of the adjacent slices in lateral direction. The masking operation may truncate some region of the brain.In order to restore the truncated region, we find the end points of the boundary of the truncated region by comparing the boundaries of the mask image and the masked image. Then, we restore the truncated region using the connectivity-based threshold segmentation algorithm with the end points. The resulting segmented image is then used as a mask for the subsequent slice.

In this paper, we propose a new directional 3-dimensional interpolation algorithm for brain magnetic resonance (MR) images. Typically, brain images consist of a number of two-dimensional images. In order to reconstruct 3 dimensional objects from slices of 2 dimensional images, interpolation operation is required. In most interpolation algorithms in the three-dimensional space, the interpolation operation is performed separately in each coordinate that is orthogonal to each other. However, since the shape of the brain is roughly a sphere, interpolation along these three orthogonal coordinates may result in some information loss, particularly when gradients of pixel values have directions similar to the directions of the coordinates. In order to address this problem, we propose a new directional interpolation algorithm. In the proposed algorithm, we first perform the interpolation along two orthogonal coordinates. Typically, the two orthogonal coordinates would be the coordinates of the two dimensional images. And then, in order to find the best interpolation in the remaining coordinate, we search various directions that are not orthogonal to the two orthogonal coordinates using cost functions. Experiments show promising results.