Multi-Modal Sensor Medical Image Fusion Based on Multiple Salient Features With Guided Image Filter

Abstract

In this paper, we propose an efficient image fusion algorithm using multiple salient features with guided image filter to prevent the problem of low contrast detail. First, we employ the guided image filter to decompose the input images into a series of smoothed and detailed images at different scales. Second, the salient features are extracted from the decomposed smoothed images and detailed images using two different algorithms: the spectral residual (SR) algorithm for extracting mainframe information and the graph-based visual saliency (GBVS) model for extracting gradient saliency information to construct the fusion rules. In addition, generalized intensity-hue-saturation (GIHS) is adopted to combine the decomposition coefficients. Finally, the fused image is reconstructed by the fused smoothed and fused detailed images. The experimental results demonstrate that the proposed algorithm can achieve better performance than other fusion methods in the domains of MRI-PET and MRI-SPECT fusion.

Keywords

• Spectral residual saliency
• graph-based visual saliency
• MRI-PET fusion
• MRI-SPECT fusion