Combining Gabor energy with equilibrium optimizer algorithm for multi-modality medical image fusion

Medical image fusion is a technique of extracting information from multiple image modalities and combining them to create a single image with the aim of improving the image content and preserving information. Until now, many approaches have been introduced to enhance efficiency in medical image fusion. Nevertheless, there are still limitations to the fusion of the low and high-frequency coefficients of several current methods to our current knowledge. The first limitation is that the output images often lose detailed information because high-frequency coefficients can be fused by ineffective rules. The second limitation is the deterioration of the resulting image luminance when the low-frequency coefficients are fused by the average rule. In this study, we propose a novel method to overcome the limitations mentioned above, and this approach is described by several steps as follows. Firstly, the discrete stationary wavelet transform (DSWT) method is used to convert input images into high and low-frequency components. Secondly, a rule based on maximum Gabor energy (MGE) is introduced to fusing high-frequency coefficients, which allows important information to be preserved in the resulting image. Thirdly, low-frequency coefficients are fused by optimal parameters based on the equilibrium optimizer algorithm (EOA). This fusion rule ensures the resulting image has good quality. In order to verify our approach's effectiveness, we have used six image quality indexes and the latest five medical image fusion methods for comparison. The experimental results show that the proposed approach has overcome the disadvantages of some current methods.