A Multi-modal Medical Image Fusion Method in Spatial Domain

Abstract

Multi-modal medical image fusion technology is playing an increasingly important role in many clinical applications. In this paper, a fast and effective multi-modal medical image fusion method in spatial domain is proposed. In our method, a moving frame based decomposition framework is adopted to decompose source images to texture components and approximation components. In addition, a novel weight map refined strategy based on image properties and guide filtering is proposed, and the final map is applied to fuse the approximation components. Experimental results demonstrate that the proposed method can achieve promising results for fusion of multi-modal medical images.