wKSR-NLM: An Ultrasound Despeckling Filter Based on Patch Ratio and Statistical Similarity

Ambrosanio, Michele; Kanoun, Bilel; Baselice, Fabio

doi:10.1109/access.2020.3014909

Cited by 7 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We thus compare our method with the standard Non-Local Means (NLM) [5] and Optimized Bayesian Non-Local Means (OBNLM) [6] methods. Non-local means methods have been shown to outperform other ultrasound de-speckling algorithms [7], [32], and are to date competitive [32], [33].…”

Section: A Baselinesmentioning

confidence: 98%

See 1 more Smart Citation

Ultrasound Speckle Suppression and Denoising using MRI-derived Normalizing Flow Priors

Schaft¹,

Sloun²

2021

Preprint

View full text Add to dashboard Cite

Ultrasonography offers an inexpensive, widelyaccessible and compact medical imaging solution. However, compared to other imaging modalities such as CT and MRI, ultrasound images notoriously suffer from strong speckle noise, which originates from the random interference of sub-wavelength scattering. This deteriorates ultrasound image quality and makes interpretation challenging. We here propose a new unsupervised ultrasound speckle reduction and image denoising method based on maximum-a-posteriori estimation with deep generative priors that are learned from high-quality MRI images. To model the generative tissue reflectivity prior, we exploit normalizing flows, which in recent years have shown to be very powerful in modeling signal priors across a variety of applications. To facilitate generaliation, we factorize the prior and train our flow model on patches from the NYU fastMRI (fully-sampled) dataset. This prior is then used for inference in an iterative denoising scheme. We first validate the utility of our learned priors on noisy MRI data (no prior domain shift), and then turn to evaluating performance on both simulated and in-vivo ultrasound images from the Plane-wave Imaging Challenge in Medical UltraSound (PICMUS) and Challenge on ultrasound beamforming with deep learning (CUBDL) datasets. The results show that the method outperforms other (unsupervised) ultrasound denoising methods (nonlocal means (NLM) and Optimized Bayesian nonlocal means (OBNLM)) both quantitatively and qualitatively.

show abstract

Section: A Baselinesmentioning

confidence: 98%

“…More recently, non-local means methods have demonstrated excellent performance in speckle reduction [31], [32]. We thus compare our method with the standard Non-Local Means (NLM) [5] and Optimized Bayesian Non-Local Means (OBNLM) [6] methods.…”

Section: A Baselinesmentioning

confidence: 99%

Ultrasound Speckle Suppression and Denoising using MRI-derived Normalizing Flow Priors

Schaft¹,

Sloun²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…An optimized Bayesian nonlocal means (OBNLM) [ 13 ] method is also introduced for speckle reduction which is based on the similarity of the patches of pixels. Later, to eliminate the drawback of over-smoothing and to enable texture preservation, non-local methods with different similarity measures are also introduced, see [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Despeckling and enhancement of ultrasound images using non-local variational framework

Febin

Jidesh

2021

Vis Comput

View full text Add to dashboard Cite

Speckles are introduced in the ultrasound data due to constructive and destructive interference of the probing signals that are used for capturing the characteristics of the tissue being imaged. There are a plethora of models discussed in the literature to improve the contrast and resolution of the ultrasound images by despeckling them. There is a class of models that assumes that the noise is multiplicative in its original form, and transforming the model to a log domain makes it an additive one. Nevertheless, such a transformation duly oversimplifies the scenario and does not capture the inherent properties of the data-correlated nature of speckles. Therefore, it results in poor reconstruction. This problem is addressed to a considerable extent in the subsequent works by adopting various models to address the data-correlated nature of the noise and its distributions. This work introduces a weberized non-local total bounded variational model based on the noise distribution built on the Retinex theory. This perceptually inspired model apparently restores and improves the contrast of the images without compromising much on the details inherently present in the data. The numerical implementation of the model is carried out using the Bregman formulation to improve the convergence rate and reduce the parameter sensitivity. The experimental results are highlighted and compared to demonstrate the efficiency of the model.

show abstract

“…Alex and Chandy (2020) changed the edges and different features in the evaluation of inpainting in speckled noisy images. The concept of non-local filter used here shows the statistical metric based on the ratio between two patches on breast tumor datasets (Ambrosanio et. al, 2020).…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Despeckling of Ultrasound Images Using Cellular Automata-Based Despeckling Filter

Bhardwaj

Kaur

Shukla

et al. 2021

International Journal of E-Health and Medical Communications

View full text Add to dashboard Cite

Ultrasound images have an inherent property termed as speckle noise that is the outcome of interference between incident and reflected ultrasound waves which reduce image resolution and contrast and could lead to improper diagnosis of any disease. In different approaches for reducing the speckle noise, there exists a class of filters that convert multiplicative noise into additive noise by using algorithmic functions. The current study proposes a cellular automata-based despeckling filter (CABDF) that implements a local spatial filtering framework for the restoration of the noisy image. In the proposed CABDF filter, a dual transition function has been designed which emphasizes the calculation of nearby weighted separation whose loads originate from the CABDF filtered image, including spatial separation, extend inconsistency, and statistical dispersion. The proposed filter found efficient both in terms of filtering and restoration of the original structure of the ultrasound images.

show abstract

wKSR-NLM: An Ultrasound Despeckling Filter Based on Patch Ratio and Statistical Similarity

Cited by 7 publications

References 41 publications

Ultrasound Speckle Suppression and Denoising using MRI-derived Normalizing Flow Priors

Ultrasound Speckle Suppression and Denoising using MRI-derived Normalizing Flow Priors

Despeckling and enhancement of ultrasound images using non-local variational framework

A Novel Method for Despeckling of Ultrasound Images Using Cellular Automata-Based Despeckling Filter

Contact Info

Product

Resources

About