Optimized Adaptive Based Method for MR Image Denoising

In this paper, we aim to utilize the orca optimization algorithm (OOA) as a computational intelligence method combined with a non-linear data-driven function in the optimization process for brain image de-noising. This meta-heuristic population-based optimizer has recently been proposed to solve complex optimization problems and has achieved promising results in various domains. Here, it is used to obtain the optimum threshold value and other parameters for the activation function. We investigate the impact of this novel algorithm compared to other state-of-the-art optimizers and alternative approaches such as Cuckoo Search (CS), Particle Swarm Optimization (PSO), Differential Evolution (DE), Thresholding Neural Network (TNN), Neighboring Wavelet Coefficients (Neishrink), Hard and Soft thresholds. Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) are also used to measure the performance analysis of various de-noising approaches. The results show that the proposed method performs better than other alternative optimization techniques.