A medical image fusion method based on SIST and adaptive PCNN

In order to improve the performance of medical image fusion, a novel medical image fusion method is proposed based on Shift-invariant Shearlet Transform (SIST) and adaptive Pulse coupled neural network (PCNN). Firstly, SIST is employed to decompose source images respectively, to get one low-pass sub-image and some band-pass directional sub-band images, which have the same size as source images. Secondly, the fusion rule based on the local energy and the local variance is used to fuse low frequency coefficients, meanwhile, the fusion rule based on adaptive PCNN is used to fuse band-pass directional sub-band coefficients, here, the improved spatial frequency(SF) in SIST domain is used as the input of PCNN model, and the gradient energy (EOG) is used as the link strength of the PCNN model. Finally, the final fused image is obtained by the inverse SIST. Compared with other methods, this proposed can not only well preserve the useful information from the source images, but also improve the accuracy of the fusion image effectively.