LPPCNN: A Laplacian Pyramid-based Pulse Coupled Neural Network Method for Medical Image Fusion

Abstract

ABSTRACT Medical image fusion technology plays an important role in clinical application, because it contains multimodal image information. The fusion effect of medical images conforms to human visual perception. Therefore, reducing the impact of prior knowledge on the fusion effect and enhancing the detail expression have always been the direction of medial image fusion. A medical image fusion method based on Laplacian pyramid and pulse coupled neural network is proposed in this paper. To solve the problem of image artifacts, the region Laplace pyramid is adopted to improve the pulse coupled neural network in order to save more detailed information and make parameters adaptive in the network. The source images are decomposed into Laplacian pyramids, and the improved pulse coupled neural network is used to generate the optimal weight graph to guide the fusion process. The fused images are generated by the reverse process. The experimental results show that compared with the state-of-the-art fusion methods, in terms of subjective effect, the fused image in this paper can retain the edge information of the source image and obtain better visual effect. In terms of objective indicators, the fused images obtained by the proposed method can achieve better results such as mutual information (MI), edge evaluation factor (QAB/F ) and structural similarity (SSIM).