Vector Quantization

After performing the preprocessing steps explained in the previous section, we obtain multispectral data G e IR(mx,my,l,n) consisting of n correctly aligned, normalized data sets, where extracerebral voxels are excluded by a presegmentation mask. This can be interpreted as follows.

Each voxel of the multispectral 3D data set represents an n-dimensional feature vector x that is determined by the tissue class for this voxel:

FIGURE 7 Segmentation. (a) T1 weighted image of a 3D data set. (b) Corresponding segmented image with gray-level representation of the tissue classes (medium gray = "gray matter," light gray = "white matter," dark gray = "CSF").

FIGURE 7 Segmentation. (a) T1 weighted image of a 3D data set. (b) Corresponding segmented image with gray-level representation of the tissue classes (medium gray = "gray matter," light gray = "white matter," dark gray = "CSF").

FIGURE 8 Manual labeling of tissue classes for supervised learning. The labeled regions (medium gray = "gray matter,'' light gray = "white matter,'' dark gray = "CSF") provide the training data set for supervised learning of the output weights Sj of the GRBF network.

determined by minimal free energy VQ presented in Section 3.1, where the update of the codebook vectors Wj is performed employing the batch version of the algorithm:

0 0

Post a comment