Most of current algorithms of image fusion are based on wavelet transform and the importance of the fusion algorithm in approximation coefficients and the information of neighbor region in detail coefficients are not sufficiently taken into account, thus failing to get perfect fusion effect in some circumstances. A new wavelet image fusion algorithm based on the analysis of the neighbor region energy of the wavelet coefficients is proposed. This algorithm fully considers the approximation coefficients fusion algorithm, the information of neighbor region in detail coeffcients and the characteristics of FDG and MRI images. By employing different masks, the algorithm integrates the approximation coefficients and the detail coefficients differently according to the weights, which are the energy of the corresponding neighbor region of the wavelet coefficients. Reconstructed from the integrated coefficients, the image contains almost all useful information of the original images. Evaluations of the experiment results according to both the subjective and objective criteria demonstrats that the proposed algorithm is more effective than the traditional algorithms.