A Complementary Global and Local Knowledge Network for Ultrasound denoising with Fine-grained Refinement

TL;DR

This paper introduces a novel ultrasound denoising network combining global and local feature extraction with fine-grained refinement, significantly improving image quality while preserving details.

Contribution

The proposed architecture integrates a L-CSwinTransformer encoder with CNN decoder and a Fine-grained Refinement Block, advancing ultrasound denoising techniques.

Findings

Achieves competitive quantitative metrics on HC18 and BUSI datasets.

Enhances image detail preservation compared to existing methods.

Demonstrates superior visual quality in denoised ultrasound images.

Abstract

Ultrasound imaging serves as an effective and non-invasive diagnostic tool commonly employed in clinical examinations. However, the presence of speckle noise in ultrasound images invariably degrades image quality, impeding the performance of subsequent tasks, such as segmentation and classification. Existing methods for speckle noise reduction frequently induce excessive image smoothing or fail to preserve detailed information adequately. In this paper, we propose a complementary global and local knowledge network for ultrasound denoising with fine-grained refinement. Initially, the proposed architecture employs the L-CSwinTransformer as encoder to capture global information, incorporating CNN as decoder to fuse local features. We expand the resolution of the feature at different stages to extract more global information compared to the original CSwinTransformer. Subsequently, we integrate Fine-grained Refinement Block (FRB) within the skip-connection stage to further augment features. We validate our model on two public datasets, HC18 and BUSI. Experimental results demonstrate that our model can achieve competitive performance in both quantitative metrics and visual performance. Our code will be available at https://github.com/AAlkaid/USDenoising.