Medical Image Synthesis Workbench Supporting Multiple Modalities With Feature-Level Transforms

Multi-modal In recent years, medical image synthesis has arisen as a holistic analytic strategy that typically employs many transformation methods. When it comes to medicine, multi-modal image synthesis refers to the technique of combining images from several imaging modalities to enhance image quality while maintaining detail. Image processing, computer apparition, pattern acknowledgment, machine knowledge, and artificial intellect are just few of the many cutting-edge fields that fall under the umbrella of medical image synthesis. The synthesis of many medicinal imaging modalities has been used extensively in the clinic to help doctors better understand the lesion. This paper presents the firefly algorithm, a multi-learning model workbench that minimises squared errors and maximises synthesis quality via weighted entropy. MATLAB simulations are used to compare the proposed workbench against state-of-the-art methods in terms of peak signal-to-noise ratio, Mean square error, correlation, and precision. The proposed workbench performs well across the board and requires less computing power.