Principal Component Analysis and Dual-Tree Complex Wavelet Transform-Based Medical Image Fusion Algorithm

A Medical image fusion facilitates medical research initiatives and improves diagnostic accuracy by exposing intricate inter-image relationships. The primary objectives are to identify different medical problems and integrate relevant data from multiple source photos into a single image. Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are two imaging modalities from which complex information can be extracted thanks to the multi-stage fusion network. Each image is subjected to the Dual Tree Complex Wavelet Transform (DTCWT), which captures intricate features and produces cross-connected data. To create a segmented output, the fused image is segmented. The method was successfully applied to about 60 photos, enabling performance comparison with alternative methods. The technique yields an accuracy result of 99.42%, a sensitivity measure of 94%, and a specificity measure of 97%. The recommended fusion procedure produces images with improved edges, tissue structure, spectral data, contours and spatial resolution which leads to enhanced tumor visualization.