SELECTION OF MR-IMAGES FOR AUTOMATED SEGMENTATION

MR images show a large range of contrast for various tissues in the bo dy and are ideal for multispectral segmentation, Typically, only two M R images (dual-echo series) are used for segmentation; however, other images are often available, We evaluated MR images from 40 patients to determine the optimal type and number of images required for segmenta tion of tissues associated with brain tumors (normal brain, edema, nec rosis, and active tumor), Pattern recognition methods indicated that t hree MR images from the same slice location were adequate for segmenta tion, as defined by feature selection and feature extraction measures based on training fields, This result was also confirmed by visually e xamining segmented images for all 40 patients, This work demonstrates that by using existing image/statistical analysis techniques (feature selection and feature extraction), one can systematically determine th e optimal type and number of MR images for tissue segmentation.