Generalized Multi-modal Medical Image Fusion Method using NSML and WLF in NSST Domain and YIQ color space

Abstract

Unimodal or multimodal medical image fusion is a powerful technique to aid in medical diagnosis. However, this fusion remains dependent on the methods chosen, and on the type of color or gray level images. In this paper, we propose a generalization of the multimodal medical image fusion technique to take as input color-converted images without distorting the merged image neither spatially nor spectrally. To carry out this work, two phases are necessary: (i) preprocessing and (ii) modal fusion. For the first phase, it is a question of converting all the gray level images into a color image in the RGB base. The outputs of the preprocessing phase will be consumed in the fusion phase regardless of their modality as YIQ color images. We then identify the low frequency (LF) sub-bands and the high frequency (HF) from the Y components based on the non-subsampled shear transform (NSST). Subsequently, the LF sub-images are combined using the weight local feature (WLF) merging rule while the HF sub-images are merged using the sum-modified-laplacian (NSML) technique. Finally, to obtain the merged image we apply the inverse NSST and inverse YIQ. To assess the performance, various experiments conducted on different datasets.