Medical Image Fusion Using Non-subsampled Shearlet Transform and Improved PCNN

摘要

Image fusion is an effective method to increase the accuracy of clinical diagnosis, since it can combine the advantages of a series of diverse medical images. In this paper, a novel image fusion method based on non-subsampled shearlet transform (NSST) and improved pulse coupled neural network (PCNN) is proposed. As an efficient multi-resolution analysis tool, NSST is used to obtain a series of sub-bands with different scales and directions. Then, the traditional PCNN is improved to be a novel model with much less parameters. Certain fusion rules are utilized to complete the fusion process of sub-bands. Finally, the inverse NSST is conducted to obtain the final fused image. Experimental results demonstrate that the proposed method has much better performance than those typical ones.