A Feature Similarity and Directive Contrast Based Multi-Modal Medical Image Fusion Technique Using Stationary Wavelet Transform

Image fusion is a critical domain in image processing that integrates two or more compromised or obscured images into a single, clearer, and more informative result. Multi-modal medical image fusion (M3IF), a category of image fusion, amalgamates images from many medical modalities into a single complete image, hence augmenting diagnostic efficacy. This research examines the integration of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) to enhance the precision and detail of medical visualization. The suggested hybrid approach (M3IF-FSIM-DC) utilizes Stationary Wavelet Transform (SWT) to decompose input medical CT and MRI images into low-frequency components (LFC) and high-frequency components (HFC). The LFC are amalgamated using the Feature Similarity Index Metric (FSIM), therefore preserving structural and feature- based information. The HFC are integrated using a directive contrast-based fusion rule that maintains edge details and minimizes artifacts. This hybrid M3IF-FSIM-DC methodology tackles significant issues in medical image fusion, such as the loss of intricate features, edge blurring, and distortion, while improving visual quality and parametric precision. M3IF-FSIM-DC enhances diagnostic understanding by preserving more essential information from each modality, surpassing current procedures. The improved fusion quality enables medical practitioners to understand intricate medical images more effectively, offering a more reliable instrument for clinical decision-making and analysis.