A Multi-Modal Medical Image Fusion Technique Using Non-Subsampled Contourlet Transform and Non-Subsampled Shearlet Transform

In image processing, "image fusion" refers to the technique of merging features from images acquired through different medical modalities to produce a more comprehensive and informative result. Multi-modal medical image fusion is a critical subset, involving modalities such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and X-rays. In this study, CT and MRI images are fused using a hybrid approach that applies Non-Subsampled Contourlet Transform (NSCT) and Non-Subsampled Shearlet Transform (NSST). The input images are initially directed to NSCT, where low-pass sub- bands (LPSB) are broken down further suing NSST, and then their LPSB are fused with average fusion rule, while the high-pass sub-bands (HPSB) are fused using maximal operation. The HPSB of NSCT are fused using threshold based fusion rule. This approach addresses common limitations in image fusion, such as loss of edge details, distortion, and the inability to preserve critical information. The hybrid M3IF-NSCT-NSST method improves both the visual quality and parametric accuracy of the fusion, outperforming comparable techniques. By preserving more detail and edge information, this method offers significant advancements in multi-modal medical image fusion for enhanced diagnostic insights.