A hybrid genetic algorithm for medical image registration with Downhill Simplex method

An hybrid genetic algorithm was proposed to perform the optimal parameters for image registration. The genetic algorithm (GA) was combined with the Downhill Simplex search, and the GA algorithm considered the adaptive probabilities of mutation which change with the fitness distance correlation (FDC), mutual information (MI) was used as metric in this paper. The results using the hybrid genetic algorithm are compared with those using the simple genetic algorithm, experimental results show that the proposed algorithm is robust and accuracy.