Enhanced Medical Image Fusion Through Laplacian Pyramid Decomposition and Weighted Averaging

This work provides a medical image fusion method to improve image quality and preserve important diagnostic features by use of Laplacian Pyramid Decomposition and weighted averaging. The method breaks images into several layers, using Laplacian pyramids to capture high-frequency components and then reconstructs them with weighted averaging. Using this approach to multi-modal medical images such as Magnetic Resonance Imaging and Positron Emission Tomography scans improves visual quality and information retention noticeably. Using entropy of 4.8615, standard deviation of 86.9258, and structural similarity index of 0.9395, experimental results show better clarity and fusion performance, therefore offering important information for clinical diagnosis and treatment planning.