Nowadays, medical imaging becomes a common part of everyday clinical practices. Despite enormous progresses, still there is no single modality which can represent all aspects of the human body. For example, CT is suitable to view dense structures while MRI provides high resolution for soft tissue. In this paper, we propose a new method for fusion of multimodal medical images. First, the surfacelet transform is used to decompose the source images. Then, we effectively combine the low and high frequency coefficients of both the source images. Finally, the fused image is computed through the inverse transform. Experimental results demonstrated the superior solution quality of the proposed approach compared to a number of well-known counterpart algorithms.

Keywords