Mitigating Noise from Biomedical Images Using Wavelet Transform Techniques

Medical imaging plays a pivotal role in modern healthcare, enabling accurate diagnosis and effective treatment planning across various medical conditions. Advanced modalities, such as magnetic resonance imaging (MRI), computed tomography (CT), and ultrasound, offer critical insights into the structure and function of the human body. However, these images are often degraded by noise introduced during acquisition or processing, potentially obscuring vital diagnostic details and impacting clinical decision-making. Furthermore, enhancement techniques like histogram equalization, while improving visual appeal, may inadvertently amplify existing noise, such as salt-and-pepper distortions. This study investigates wavelet transform-based denoising methods to mitigate noise in medical images effectively. Our primary goal is to identify the optimal combination of threshold values, decomposition levels, and wavelet types to achieve superior denoising performance, ensuring enhanced diagnostic accuracy. Our study finds that the db3 wavelet with universal thresholding achieved the best denoising effect across various noise levels. For noise standard deviations of σ = 10, 15, and 25, the best PSNR values obtained are 29.203 dB, 27.791 dB, and 25.194 dB, respectively. These results establish a foundation for developing hybrid wavelet-deep learning approaches for medical image denoising.