Application of Genetic Algorithm in Denoising MRI Images Clouded with Rician Noise

Abstract

In this research Genetic Algorithm (GA) is suggested for remotion of Rician Noise. This type of disturbance primarily occurs in low signal to noise (SNR) regions. Original low signal is clouded due to presence of Rician noise and measurement gets hindered in low SNR areas. To defeat the trouble real and imaginary data in the image field are rectified, before construction of the magnitude image. The noise diminution filtering (or denoising) is attained by Genetic Algorithm. New genetic manipulator is used that blends crossover and adaptive mutation to improve the convergence rate and solution quality of GA. For validating the results, the proposed filter was tested successfully by keeping the number of generations fixed and gradually increasing the noise level. Similar trends of decrease were obtained in the mean square error values after the filtering was performed. This new proficiency efficaciously reduces the standard deviation and significantly lowers the rectified noise after the filtering was performed.