A Method for Removing Speckle Noise in Ultrasound Images

Abstract

The invention discloses a method for removing speckle noise in an ultrasonic image. In the first iteration, a noise image is used as the input of a model, and a rough despeckle image is obtained after filtering by a Bayesian non-local average filtering model; In the second iteration, the obtained de-speckled image is used as the input of the filtering model to obtain a better de-speckled image; the iterative process is repeated until the number of iterations reaches a preset value. A good de-speckled image is finally output through a benign iterative filtering process. The advantage of the present invention is that the adverse effects of speckle noise on clinical diagnosis or subsequent image processing are suppressed. Combined with the statistical characteristics of speckle noise, the conditional probability density function value in the Bayesian non-local average filtering model is calculated, and a better de-speckled image will be output through a benign iterative filtering process. In order to reduce the time complexity of the algorithm, three means of block filtering, pre-selecting blocks and controlling the number of iterations are used to make the method practical.

Description

technical field [0001] The invention relates to the technical field of ultrasonic image processing, in particular to a method for removing speckle noise from an ultrasonic image. Background technique [0002] Ultrasound imaging technology is a convenient and fast imaging technology, which is widely used in human body examination, especially in liver, gallbladder, pancreas, abdomen, breast and other parts. Compared with CT imaging technology, ultrasound imaging is much safer, eliminating the possible radiation damage caused by human body exposure to X-rays; Important imaging modality for round disease screening. However, the images acquired by current ultrasonic instruments are inevitably disturbed by speckle noise, which is caused by the coherent characteristics of ultrasonic system imaging. The existence of speckle noise reduces the resolution and contrast of the image, reduces the quality of the image, and conceals some detailed information, which is useful for clinical ...

AI Technical Summary

Problems solved by technology

However, the speckle noise is different from the Gaussian noise considered in the usual image denoising problem. From the morphological point of view, it presents the effect of granular or serpentine spots. From the point of view of noise statistical characteristics, its noise generation model is different from additive Gaussian. Therefore, it is impossible to directly transfer the existing denoising method to the elimination of speckle noise, but it is necessary to fully consider the characteristics of speckle noise in the denoising model, improve the existing model, and give full play to the existing denoising technology The effect on speckle noise removal

Images