Multimodal medical image fusion based on edge enhancement and detail preservation

We propose a multimodal medical image fusion method based on edge enhancement and detail preservation to address the issue of lost image details in current medical image fusion approaches. Firstly, we decompose the images from different modalities using the non-subsampled shearlet transform (NSST) to obtain their respective high-frequency and low-frequency subbands. Next, we employ a novel detail-preserving parameter adaptive pulse coupled neural network to fuse the high-frequency subbands, and an edge-enhanced weighted local energy method to fuse the low-frequency subbands. Finally, the fused image is reconstructed by performing inverse NSST on the fused high-frequency and low-frequency subbands. Experimental results demonstrate that our proposed method effectively preserves more detailed information from the source images and exhibits excellent performance in both subjective and objective evaluations when compared to seven commonly used multimodal medical image fusion methods.