Multi-modal Medical Image Fusion Based on the Multiwavelet and Nonsubsampled Direction Filter Bank

Aiming at solving the fusion problem of multimodal medical images, a novel medical image fusion algorithm is present in this paper. The multiwavelet is combined with the NSDFB to construct the proposed Multi-NSDFB transform. The source images can be decomposed into several lowpass coefficient and highpass coefficient. And all coefficients can be decomposed into four direction subbands. The modified spatial frequency is adopted to motivate the pulse coupled neural network to select the every direction subbands coefficients. Experiment results demonstrate that the proposed algorithm can not only extract more important visual information from source images, but also effectively avoid the introduction of artificial information. The present scheme outperforms the redundant discrete wavelet transform-based, and the Ripplet transformbased in terms of both visual quality and objective evaluation.