Multigrid Nonlocal Gaussian Mixture Model for Segmentation of Brain Tissues in Magnetic Resonance Images

Figure 4

Segmentation results of synthetic data with the parameter noise level 5% and INU level 80%. The left column shows the initial image. The second column to the fifth column show the results of GMM, Wells, MCFC, and MNGMM, respectively. The right column is the ground truth.