A New Hybrid Medical Image Fusion Method Based on Fourth-Order Partial Differential Equations Decomposition and DCT in SWT domain

In this paper, a new hybrid method based on fourth-order partial differential equations (FPDE) and discrete cosine transform (DCT) in stationary wavelet transform (SWT) domain is proposed for fusing the multimodality images such as CT and MRI. First, the input images are decomposed into base and detail images using fourth-order differential equations method. Final detail image is obtained by weighted average of principal components of detail images. Next, the base images are given as input for SWT decomposition. The corresponding four subband coefficients are processed using DCT. DCT is used to extract significant details of the subband coefficients. Spatial frequency of each coefficient is calculated to improve the extracted features. At last, fusion rule is used to fuse DCT coefficient's based on spatial frequency value. Final base image is obtained by applying inverse DCT and inverse SWT. By combining the above final detail and base images linearly, a final fused image is generated. The comparative analysis of proposed method with the existing fusion algorithms is carried out. From the results it is observed that proposed method gives better performance in terms of objective criteria like mean, STD, MI, FMI, etc., than the existing methods.