Robust non-local means filter for ultrasound image denoising
This is an incremental improvement for medical imaging, specifically enhancing ultrasound image quality for diagnostic purposes.
The paper tackles ultrasound image denoising by proposing a robust non-local means filter that identifies and downweights highly corrupted pixels, resulting in good performance in recovering edge shapes and details compared to traditional methods.
This paper introduces a new approach to non-local means image denoising. Instead of using all pixels located in the search window for estimating the value of a pixel, we identify the highly corrupted pixels and assign less weight to these pixels. This method is called robust non-local means. Numerical and subjective evaluations using ultrasound images show good performances of the proposed denoising method in recovering the shape of edges and important detailed components, in comparison to traditional ultrasound image denoising methods