A novel variational optimization model for medical CT and MR image fusion

In medical imaging processing, image fusion is the process of combining complementary information from different or multimodality images to obtain a high-quality and informative fused image in order to improve clinical diagnostic accuracy. In this paper, we propose a novel variational fusion model based on contrast and gradient features, the weight images and the fused images are constrained by the total variation regularization. The salient contrast features and clear soft tissue structure information of source CT and MR images can be preserved in the fused images. The variational problem is solved by a fast split optimization algorithm. In the numerical experiments, the proposed method is compared with seven state-of-the-art methods, and the comparison metrics MI, Q(W) and Q(G) are calculated for assessment. The proposed method shows a comprehensive advantage in preserving the contrast features as well as texture structure information, not only in visual effects but also in objective assessments.