Segmentation Of 3D Brain Using an Adaptive K-means Algorithm

To segment the 3D medical image using K-Means clustering algorithm for 3-dimensional and multi-valued images that can be better for large datasets and to find initial centroid. In order to compare the performance an algorithm is described for segmenting 3D MR brain image into K different tissue types, which include gray, white matter and CSF, and maybe other abnormal tissues.MR images considered can be either scaled or multi-valued.