In recent years, many solutions to medical diagnostic image fusion have been proposed; however, it is difficult to simulate the surgical ability of image fusion when algorithms of image processing are piled up merely. On the basis of the review of researches on psychophysics and physiology of human vision, this paper presents an effective multi-resolution image fusion methodology, which is self-organizing feature mapping wavelet neural network (SOFMWNN), to simulate the processes of images recognition and understanding implemented in the human vision system. As an example, the fusion process is applied in the clinical case: the study of some particular disease by MR/SPECT fusion. Results are presented and evaluated, and a preliminary clinical validation is achieved. The effectiveness of the proposed model is demonstrated via results comparison with several other image fusion methods.