A Computational and Comparative Analysis of Medical Image Fusion Using Different Transform Domain Techniques

Medical image fusion plays a critical role in enhancing diagnostic accuracy and the clinical decision-making process by combining information from multiple medical imaging modalities. Transform domain techniques have shown promising results in medical image fusion, as they effectively capture the transform-based information present in the images. This paper presents a comprehensive comparative study of medical image fusion using different transform domain techniques. Each technique is applied to diverse medical images, such as MRI, CT, and PET, representing different anatomical structures and pathological conditions. For each transform domain technique, we analyze the fusion process, including decomposition, fusion rules, and reconstruction. The computational complexity of each algorithm and performance evaluation is conducted using objective fusion metrics with the help of MATLAB software. Furthermore, we evaluate the robustness of the techniques under varying noise levels, image artifacts, and fusion parameters. Our experimental results reveal that each transform domain technique has its strengths and limitations, depending on the specific imaging modality and clinical application. Overall, this comparative study contributes to medical image fusion research advancement, guiding researchers and practitioners in choosing the most suitable transform domain technique for enhancing medical image interpretation, disease diagnosis, and treatment planning.