Improving the Convergence Rate in Affine Registration of PET and SPECT Brain Images Using Histogram Equalization
Figure 3
Circles: mean normalised cost function value of 50 images versus number of iterations for the original PET brain images with intensity values expanded from 0 to 1. Rectangles: mean normalised cost function calculated applying the affine matrix calculated in each iteration using the preprocessed PET images to the original brain PET images. Dotted red line: mean normalised cost function value of 50 images versus number of iterations for preprocessed images using histogram matching.