Magnetic resonance imaging-clonal selection algorithm: An intelligent adaptive enhancement of brain image with an improved immune algorithm

摘要

Artificial Immune System is used nowadays to solve complex problems, including medical problems. To overcome some flaws of traditional clonal selection algorithm in medical imaging applications, a novel clonal selection algorithm in intelligent adaptive enhancement design of magnetic resonance imaging (MRI) brain images is proposed. It is called the MRI-Clonal Selection Algorithm (MRI-CSA). The MRI-CSA uses three improvements for the Clonal Selection Algorithm. Firstly, instead of the simple binary coding, the real coding approach of the MRI brain image is designed. Secondly, the mutation distance is added into the mutation operator to better control the mutation progress and avoid any narrow local optimization. Finally, both the clone selection and the mutation are adjusted together in the Gauss distribution, the uniform distribution, and the chaotic distribution, rather than in only the Gauss distribution. In addition, the real MRI brain images are used in the image enhancement testing with our improved clonal selection algorithm. The experimental results show that the proposed approach outperforms the median filtering (MF) and the adaptive template filtering (ATF) in enhancing the MRI brain images.