Speckle Noise Reduction in Medical Ultrasound Images

TL;DR

This paper introduces a novel speckle noise reduction method for ultrasound images using logarithmic transformation combined with anisotropic diffusion tensor, improving image clarity for better diagnosis.

Contribution

It proposes a new denoising approach that effectively reduces speckle noise by integrating logarithmic transformation with a non-linear diffusion tensor technique.

Findings

Enhanced image contrast and detail preservation

Effective noise reduction demonstrated on synthetic and real images

Improved diagnostic image quality

Abstract

Ultrasound imaging is an incontestable vital tool for diagnosis, it provides in non-invasive manner the internal structure of the body to detect eventually diseases or abnormalities tissues. Unfortunately, the presence of speckle noise in these images affects edges and fine details which limit the contrast resolution and make diagnostic more difficult. In this paper, we propose a denoising approach which combines logarithmic transformation and a non linear diffusion tensor. Since speckle noise is multiplicative and nonwhite process, the logarithmic transformation is a reasonable choice to convert signaldependent or pure multiplicative noise to an additive one. The key idea from using diffusion tensor is to adapt the flow diffusion towards the local orientation by applying anisotropic diffusion along the coherent structure direction of interesting features in the image. To illustrate the effective performance of our algorithm, we present some experimental results on synthetically and real echographic images.