An improved medical image synthesis approach based on marine predators algorithm and maximum Gabor energy

Multimodal medical image fusion has been attracting the attention of researchers in recent years because it supports doctors in enhancing clinical diagnosis. Improving the quality of fused images and keeping important information from the input images remain a significant challenge for the current algorithms. Therefore, an effective approach for medical image fusion is introduced in this paper to address the challenges posed above. Initially, the three-scale image decomposition method using the weighted mean curvature filter and two-scale image decomposition is introduced to decompose the input images into high- and low-frequency coefficients. Subsequently, an efficient fusion rule for high-frequency components using maximum Gabor energy is proposed. This rule allows the preservation of important information in the composite image. Ultimately, the low-frequency components are synthesized using the optimal parameters from the Marine predators algorithm. This fusion rule is designed to ensure a good quality output image. A total of 120 pairs of medical images are tested in our experiments. Five latest medical image fusion methods and six image quality metrics are used for comparing and evaluating the effectiveness of the proposed algorithm. Based on the analysis of the experimental results, the proposed algorithm has obtained better performance than the current latest algorithms.

Automated summary

This paper introduces an effective approach for medical image fusion, decomposing images into high- and low-frequency components and synthesizing them using different rules to preserve important information while ensuring output quality. Experimental results show that the proposed method outperforms current latest algorithms.