Medical image fusion based on local Laplacian decomposition and iterative joint filter

Abstract

Previous multi‐modal medical image fusion methods have suffered from color distortion, blurring, and noise. To address these problems, we propose a method for integrating the information contained in functional and anatomical medical images. In the proposed method, multi‐scale image representation of input images is produced by local Laplacian filtering. The rgb2ycbcr algorithm and iterative joint filters are then used to produce fused approximate images. The residual images are divided into regions of interest and noninterest regions, and then a local energy maximization scheme and local energy average scheme are used to combine these regions. Fused interest areas and fused noninterest areas are combined to produce fused residual images. Finally, an inverse local Laplacian filter is used as a reconstruction tool to produce a fused image. Experimental results indicated that our method has a distinct advantage over existing state‐of‐the‐art algorithms in terms of vision quality and objective metrics.

A Robust Medical Image Fusion Based on Synthetic Focusing Degree Criterion and Special Kernel Set for Clinical Diagnosis

“…The rolling guiding filter is then used to filter the detailed images produced by deducting the cross bilateral filter image output from the original images in order to enable scale-aware operation. Many recent studies have employed image transformation techniques, including wavelet transform-based approaches (Tawfik et al, 2021), Laplacian Decomposition (LD) (Li et al, 2022) and Laplacian Pyramid (LP) transform (Fu et al, 2020).…”