Mutual Information Metric Evaluation for PET/MRI Image Fusion

Abstract

Image fusion developments has paved way for new approaches like image overlay, image sharpening, and image cueing through pixel, feature, or region/shape combinations. The applicability of these new techniques differs on the image content, contextual information, and generalized metrics of image fusion gain. An image fusion gain can be assessed relative to information gain or entropy reduction. In this paper, we are interested in exploring the performance metric evaluation of the fused images. The metric evaluation method for the fused image is done by studying the mutual information content of the images of interest. The registered MR/PET images are used for demonstration. Mutual Information is proposed as an information measure for evaluating image fusion performance. The proposed measure represents how information obtained from the fused image can be used to assess the information of different image fusion algorithms. The results show that the measure is meaningful and explicit.