Multi-modal MRI image fusion of the brain based on joint bilateral filter and non-subsampled shearlet transform

Multi-modal brain MRI image fusion is one of the hottest discussed issues in the current research of medical image processing and has a deep impact on brain science and diagnosis. In this study, a fusion algorithm based on the joint bilateral filter (JBF) and the non-subsampled shearlet transform (NSST) is proposed. First, the multi-modal brain MRI images were decomposed by NSST and JBF models to derive the high-frequency component and energy layer. Secondly, the corresponding energy layer images and high-frequency components are fused. Thirdly, the inverse NSST transform is performed on the energy layer fusion image and the high-frequency fusion image to obtain the ultimate fusion image. Finally, the algorithm was evaluated using a publicly available brain dataset. The experimental results show that the algorithm achieves good performance in terms of both subjective evaluation and objective metrics.