Color PET-MRI Medical Image Fusion Combining Matching Regional Spectrum in Shearlet Domain

Abstract

The color PET-MRI medical image fusion is a growing research area in medical image processing domain. MRI imagery provides the picture of the anatomy of brain tissues without any functional information, while the color PET imagery gives the functional information of brain tissues with low spatial resolution. An ideal fusion model should maintain both the functional and spatial information of the images without any spatial distortion or color deformation. In this work, we present a novel fusion technique for color PET-MRI medical images using Two-Dimensional Discrete Fourier (2DFT)-Karhunen–Loeve transform (KLT) and singular value decomposition (SVD) in shearlet domain. This method decomposes the source images into multi-scaled and multi-directional sub-bands by shearlet transform (ST). Then, SVD is utilized to eliminate superfluous ST coefficients; later, the 2DFT and KLT are utilized to estimate optimal low-pass ST coefficients in each of the decomposed images. Later, we combine the largest low-pass ST coefficients using a novel fusion strategy. The process of decomposing the source image has been discussed in detail. Finally, we use the inverse shearlet transformation (IST) to obtain the fused image. Experimental results establish the excellence of our proposed method in terms of quantitative and qualitative evaluation criteria compared to other state-of-the-art techniques.