Review of Denoising Gaussian and Salt & Pepper Noise in MRI Images

Medical imaging plays a crucial role in diagnosing and monitoring various diseases. Magnetic Resonance Imaging (MRI) is a widely used imaging technique that provides detailed anatomical information. However, MRI images are often corrupted by different types of noise, including Gaussian noise and Salt & Pepper noise, which can degrade the image quality and hinder accurate diagnosis. This paper presents a comprehensive review of denoising techniques specifically designed for MRI images corrupted by Gaussian and Salt & Pepper noise. The focus is on the application of a modified median filter, an effective denoising method that has shown promising results in handling these types of noise. The review begins by discussing the characteristics of Gaussian and Salt & Pepper noise and their impact on MRI images. Next, various traditional and advanced denoising techniques, such as spatial filters, wavelet-based methods, and machine learning-based approaches, are explored. Furthermore, the paper highlights the advantages and limitations of these techniques in effectively reducing noise while preserving important image details. Special attention is given to the modified median filter, which incorporates adaptive thresholding and spatial context to enhance denoising performance. The algorithm’s underlying principles and implementation details are presented, along with a comparison of its performance against other denoising techniques.