Dual‐echo MRI segmentation using vector decomposition and probability techniques: A two‐tissue model

摘要: We combined a vector decomposition technique with Gaussian probability thresholding in feature space to segment normal brain tissues, tumors, or other abnormalities on dual-echo MR images. The assigns each voxel fractional volume for of two tissues. A threshold, based an assumed density function describing random noise, isolates region calculation that minimizes contamination from calculated volumes are unbiased estimates the true volumes. contrast-to-noise ratio (CNR) between tissues segmented images is same as Euclidean norm CNRs original method capable segmenting more than set by sequentially analyzing different pairs model analyzed mathematically and experiments phantom. Two clinical examples presented.