Ultrasound Image Denoising using Multiscale Ridgelet Transform with Hard and NeighCoeff Thresholding

Abstract

Ultrasound imaging utilizes sound waves reflected from different organs of the body to give local details and important diagnostic information on the human body. However, using ultrasound images for diagnosis is difficult because of the existence of speckle noise in the image. The speckle noise is due to interference between coherent waves which are backscattered by targeted surfaces and arrive out of phase at the sensor. This hampers the perception and the extraction of fine details from the image. Speckle reduction/filtering i.e. visual enhancement techniques are used for enhancing the visual quality of the images. The multscale ridgelet transform based denoising algorithm for Ultrasound images is proposed for effective edge preservation in comparison to filtering techniques using the Adaptive Filters.