Speckle noise removal in ultrasound images using sparse code shrinkage

摘要

The paper proposes a method for ultrasound image denoising by using a classical signal processing method, i.e. Independent Component Analysis. The main idea is to process ultrasound images by the sparse code shrinkage algorithm based on ICA. We use the FastICA algorithm to estimate the inverse of the unknown mixing matrix and then apply the shrinkage operator for each determined independent component. The sparse code shrinkage method is compared with other speckle noise filtering algorithms and the results obtained show that sparse code shrinkage is a good method for multiplicative noise reduction in both test images and ultrasound images.