A novel medical image fusion method based on Rolling Guidance Filtering

Abstract Medical image fusion realizes the complementary advantages of information between different modality medical images to obtain more comprehensive and precise image results. In order to better preserve valid structural information and detail textures of source images, we propose a novel medical image fusion method in this paper. Firstly, we adopt a Rolling Guidance Filter to separate source medical images into structural component and detail component. The Laplacian Pyramid based fusion rule is used to merge the structural component. For the detail component, a sum-modified-laplacian (SML) based method is employed. At last, the result is acquired by integrating the fused structural and detail components. Experimental results demonstrate that the method is superior to conventional medical image fusion methods.