Medical Image Denoising Using Wavelet Thresholding

Abstract

In medical images, noise suppression is a particularly delicate and difficult task. A tradeoff between noise reduction and the preservation of actual image features has to be made in a way that enhances the diagnostically relevant image content. The method of wavelet thresholding has been used extensively for denoising medical images. The idea is to transform the data into the wavelet basis, in which the large coefficients are mainly the signal and the smaller ones represent the noise. By suitably modifying these coefficients, the noise can be removed from the data. In this paper, we evaluate several two-dimensional denoising procedures using medical test images corrupted with additive Gaussian noise. Our results, using the peak-signal-to-noise ratio as a measure of the quality of denoising, show that the NormalShrink method outperforms the other wavelet-based techniques (VisuShrink, BayesShrink). We also demonstrate that garrote shrinkage offers advantages over both hard and soft shrinkage.

Denoising Various Imaging Modalities using Wavelets, Ridgelets and Curvelets: A Comparative Analysis

“…Wavelets, Ridgelet and Curvelets using Soft and Hard thresholding have been proposed (14), (15). Second generation Curvelets (i.e.)…”

“…In equation [15] the term f(m,n) is the original image and the term is the de-noised image. M x N is the number of pixels.…”

Automated breast cancer detection and classification using ultrasound images: A survey

“…Soft thresholding provides smoothness when applied to an image while hard thresholding preserves the features of an image. Applications of hard and soft thresholding can be found in [61,62,[73][74][75]. Most of them have focused on developing the best uniform threshold.…”

Texture analysis for ulcer detection in capsule endoscopy images

“…Many studies have investigated wavelet-based features in various applications such as image denoising [13], image compression [14] and tumor recognition in ultrasound images [15]. The success of wavelets lies in its good performance for piecewise smooth functions in one dimension, however, such is not the case in two dimensions.…”