NSCT-Based Multimodal Medical Image Fusion With Sparse Representation and Pulse Coupled Neural Network

Multimodal medical image fusion plays a vital role in clinical diagnosis and treatment planning. In the image fusion methods based on nonsubsampled contourlet transform (NSCT) and pulse coupled neural network (PCNN), authors have used normalized coefficient value to motivate the PCNN-processing, which makes the fused image blurred, detail loss and decrease in contrast. In this paper, we present a novel multimodal medical image fusion method by combining sparse representation (SR) and pulse coupled neural network (PCNN) in nonsubsampled contourlet transform (NSCT) domain. Firstly, the source images are decomposed into lowand high-frequency bands in NSCT domain, which are sparsely represented with learned dictionaries. Then `1-norm matrix is used to motivate the PCNN-processing both in lowand high-frequency bands, and large firing times are selected as coefficients of the fused image. Finally, the fused image is reconstructed by performing inverse NSCT. Experimental results show that the proposed scheme outperforms the state-of-the-art methods in subjective quality and objective evaluation criteria.