FFSWOAFuse: Multi-modal medical image fusion via fermatean fuzzy set and whale optimization algorithm

Multi-modal medical image fusion (MMIF) plays a crucial role in obtaining valuable and significant information from different medical modalities. This process has generated a single resultant image that is suitable for better clinical assessments and surgical planning. In this study, we proposed a new approach to medical image fusion via fermatean fuzzy set (FFS) and whale optimization algorithm (WOA). In the first phase, a gaussian filter was used to achieve a decomposed base and detailed layers individually. The base layers were transformed into fermatean fuzzy images (FFIs) using an optimized value $\left(\lambda \right)$, obtained by using fermatean fuzzy entropy (FFE). In the second phase, the similarity and texture-based fusion rules for decomposed blocks of two FFIs enhance the textural and contrast details. In the third phase, the whale optimization algorithm (WOA) was employed to generate optimal weights for merging the detailed layers, preserving the significant edge details. In the final stage, the quality fused image was reconstructed by incorporating the fused base and detailed layer components. This manuscript compares fifteen state-of-the-art methods and evaluates the performance of proposed work using ten performance metrics. In both a visual and quantitative sense, the outstanding fusion results demonstrate that the presented model can adequately retain better color and high contrast with significant edge features than the other fusion methods.