Ultrasound Image Denoising Based on the Contourlet Transform and Anisotropic Diffusion

In this paper, a method based on the combination of contour let transform and an isotropic diffusion for ultrasound image denoising is proposed. The goal is to remove noise from ultrasound images effectively with less loss of edge details. First, the image is decomposed using the contour let transform. Soft threshold denoising is conducted in the contour let transform domain and then the image is reconstructed. Second, the an isotropic diffusion is implemented to suppress speckle noise while preserving the edge details. Experiment result shows that the proposed method can effectively remove image noise, and it can get a higher signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR) and edge preservation values.