Anisotropic diffusion filter based fusion of NSST transformed medical images

Abstract

In this paper, an image fusion method is proposed for the fusion of MR and CT images to obtain high contrast fused image that contains complementary information from both the input images. Proposed method uses NSST based fusion method to fuse the information from the two input images, whereas to enhance the edge information and to increase the contrast in the fused image, anisotropic diffusion based fusion method is used and its result is added to the NSST based fusion method. Proposed method is analyzed and compared with five state-of-the-art fusion methods in terms of both visual perception and objective assessment. Minimum percentage improvement of the proposed method over the five state-of-the-art methods are 5.99%, 129.84%, 7.48%, 7.52%, and 5.25% respectively, whereas maximum percentage improvement of the proposed method over the five state-of-the-art methods are 18.51%, 196.52%, 29.64%, 26.35%, and 16.05% respectively.