Medical MRI Image Registration Based on the Feature Space
Jing Li · 2007
Mutual information registration based on pixel intensity has been widely used in recent years. However, its application to sub-images with small samples is questionable, because many local maximums may happen or the global maximum may be away from the actual maximum value which causes unnecessary registration error. A new approach, mutual information registration based on feature-label(MIF), is proposed to solve such problem. This method first uses image’s intensity and gradient features to train the self-organized mapping(SOM) neural network, and then builds up the feature classifier for each modal image. Using such a classifier, images are project into a feature space with decreased dimensions. Finally mutual information is evaluated in the feature space to match images. Our results demonstrate that this method increases the success rate of the sub-image registration, and is optimal for the whole images(either with or without noise) elastic registration.