Speckle Noise Reduction of Medical Ultrasound Images using Bayesshrink Wavelet Threshold

Abstract

In diagnosis of diseases Ultrasonic devices are frequently used by healthcare professionals. The main problem during diagnosis is the distortion of visual signals obtained which is due to the consequence of the coherent of nature of the wave transmitted. These distortions are termed as 'Speckle Noise'. The present study focuses on proposing a technique to reduce speckle noise from ultrasonic devices. This technique uses a hybrid model that combines fourth order PDE based anisotropic diffusion, linked with SRAD filter and wavelet based BayesShrink technique. The proposed filter is compared with traditional filters and existing filters using anisotropic diffusion. Experimental results prove that the proposed method is efficient in reaching convergence quickly and producing quality denoised images.

Multiresolution edge detection using enhanced fuzzy c-means clustering for ultrasound image speckle reduction

“…Damodaran et al, 30 Sudha et al 26,28 and Karthikeyan et al 29 achieved PSNR values of 28 db, 27-32 db, and 22.95 db, respectively. Guo et al 27 on the other hand achieved a PSNR value of 25 db and an EPI that varied from 0.5 to 0.9.…”

“…Most of these algorithms provide adequate despeckling performance; however, in many instances, valuable diagnostic information cannot be preserved. In studies by Damodaran et al, 30 Sudha et al, 26,28 and Karthikeyan et al, 29 the algorithms employed were oriented to speckle suppression and not to edge preservation. In a study by Guo et al,27 the compromise between the prerequisites of an effective speckle suppression algorithm (speckle suppression and edge preservation) led to moderate speckle suppression and edge preservation.…”

Measuring fish activities as additional environmental data during a hydrographic survey with a multi-beam echo sounder

“…Since the noises do not follow a Gaussian distribution and vary with the depth, classical methods such as the Otsu binarisation (adaptive image thresholding method) or global thresholding techniques were not really suitable. Thus, local thresholding techniques may be considered such like adaptive methods with a median kernel, or the use of a wavelet method as proposed in [28], and else combining image and learning methods like in [29].…”

Wavelet-based Image Enhancement Techniques for Improving Visual Quality of Ultrasonic Images

“…Image denoising is a technique used to remove these unwanted pixels that obscure important parts. Different hybrid denoising models that combines anisotropic diffusion and wavelets for removing noise in ultrasonic medical images were investigated [8]. This paper enhances the working of anisotropic diffusion and proposes different wavelet shrinkage models to remove noise.…”