Enhanced median filtering for denoising gaussian and salt & pepper noise in MRI images

MRI (Magnetic Resonance Imaging) is a widely used medical imaging technique that provides detailed and high-resolution images of internal body structures. However, MRI images are often corrupted by different types of noise, such as Gaussian noise and Salt & Pepper noise, which can significantly degrade image quality and affect accurate diagnosis. In this study, we propose an enhanced median filtering technique for denoising Gaussian and Salt & Pepper noise in MRI images. By comparing pixel values, outliers caused by noise are identified. For noisy pixels, an adaptive weighted median filtering operation is applied to estimate a more accurate pixel value while preserving image details. The weighting scheme emphasizes the central pixels, enhancing noise reduction while maintaining structural integrity.Experimental results demonstrate that the proposed enhanced median filtering technique effectively reduces Gaussian and Salt & Pepper noise in MRI images. The demonised images exhibit improved clarity, enhanced contrast, and reduced noise artifacts compared to the original noisy images. Quantitative evaluation metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Mean Structural Similarity Index (MSSIM), confirm the superior performance of the proposed method.