Multi-modal In recent years, medical image fusion has emerged as an all-encompassing analytic strategy that frequently makes use of a variety of various alteration methods. This trend began in the field of radiology. By integrating a large number of images obtained using a single or many imaging modalities, the purpose of multi-modal medical image fusion is to improve imaging quality while preserving certain properties of the images. Image processing, computer vision, pattern recognition, machine learning, and artificial intelligence are just a few of the many cutting-edge topics that can be categorised as part of the broader category of medical image fusion. In order to better understand the lesion, medical professionals have been making substantial use of a technique that combines a number of different medical imaging modalities. In this article, we present a framework for fusion that is based on a number of learning models that are known together as the firefly algorithm. The objective of this framework is to get rid of the squared error and optimise through weighted entropy. The performance of the suggested workbench is simulated in MATLAB and compared against approaches that are considered to be state-of-the-art in order to determine how effective it is. The peak signal-to-noise ratio, mean square error, correlation, and precision are some of the most important measures. The performance of the suggested workbench is superior according to all criteria, and it also decreases the amount of computational load.