Multimodality medical image fusion based on non-sub-sampled contourlet transform

Abstract

The fusion of medical images is an essential and effective technique for disease analysis. The current study proposed a Non Sub sampled Contourlet Transform (NSCT) image fusion technique in which Neuro Fuzzy with Binary Cuckoo Search (NFBCS) and Salp Swarm Optimisation (SSO) methods were utilised. The researchers successfully fused the images retrieved from Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) and created a single merged image which becomes a new integrated diagnostic method. At the beginning, two unique sets of images such as MRI and CT were considered for the fusion procedure. These pairs of images are used in NSCT to generate the image and divide it into high frequency module and low-frequency module. Mixing policies are used here to generate and combine high- and low-frequencies. Compared to existing techniques, the results of the proposed technical tests exhibited better processing efficiency and delivered excellent results on subjective and objective evaluation criteria. This is particularly advantageous for accurate clinical analysis of the disease. The proposed work was carried out in MATLAB program. The results were tested on the medical images of brain and spine. The outcomes were compared in terms of MSE, RMSE and entropy.