Image de-noising of Ultrasound Carotid artery images using various filters

Abstract

Stroke is one of the most important causes of death in recent days. The accumulation of plaque in the carotid artery helps in identifying the possibility of cardiovascular disease and long-term disabilities. Atherosclerosis is a disease caused by the accumulation of plaque in the carotid artery of a person. B-mode ultrasound imaging is the imaging modality that is used for early prediction of this disease. Ultrasound images are affected by speckle noise, which degrades the quality of the image. The purpose of this article is to give a widespread review and implementation of various de-noising methods to de-noise the images for further processing which aids in identifying stroke, atherosclerosis and related cardiovascular diseases. Gaussian, Anisotropic, Bilateral, Wavelet, Non-Local Mean, Total Variation, Block matching 3D filtering techniques were used to remove the speckle noise in the ultrasound B-mode carotid artery images. Therefore, work is required to reduce noise without losing main image features. Various strategies for reducing the noise in the US B-mode images have been suggested in the existing body of knowledge. Each technique has pros and cons of its own. In this article, we presented some significant image de-noising studies. First, we give the formulation of the image de-noising problem, and then outlined several image de-noising techniques. Also, we go over the features of these techniques. The effectiveness of different preprocessing approaches is compared based on performance criteria like Peak Signal to Noise Ratio (PSNR) and Speckle Suppression Index (SSI). Finally, we compared the performance of conventional de-noising filters and the results are presented.