BM3D-based ultrasound image denoising via brushlet thresholding

Gan, Yu; Angelini, Elsa D.; Laine, Andrew F.; Hendon, Christine P.

doi:10.1109/isbi.2015.7163961

Cited by 18 publications

(27 citation statements)

References 12 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preprocessing procedure includes image denoising and flattening. Given that OCT images are generally corrupted by speckle noise, 29 we used a block matching 3-D (BM3-D) 30 , 31 method to denoise OCT images and enhance the boundaries. Briefly, for the BM3-D algorithm we divide the original OCT image into multiple blocks and denoise similar blocks.…”

Section: Methodsmentioning

confidence: 99%

Automated classification of optical coherence tomography images of human atrial tissue

et al. 2016

Self Cite

View full text Add to dashboard Cite

Abstract. Tissue composition of the atria plays a critical role in the pathology of cardiovascular disease, tissue remodeling, and arrhythmogenic substrates. Optical coherence tomography (OCT) has the ability to capture the tissue composition information of the human atria. In this study, we developed a region-based automated method to classify tissue compositions within human atria samples within OCT images. We segmented regional information without prior information about the tissue architecture and subsequently extracted features within each segmented region. A relevance vector machine model was used to perform automated classification. Segmentation of human atrial ex vivo datasets was correlated with trichrome histology and our classification algorithm had an average accuracy of 80.41% for identifying adipose, myocardium, fibrotic myocardium, and collagen tissue compositions.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated classification of optical coherence tomography images of human atrial tissue

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Table 4 is the comparison between the other two improved BM3D methods [25, 27] and our improved BM3D method. From the comparison results, we can see that the improved method proposed by us is better.…”

Section: Resultsmentioning

confidence: 99%

“…Many optimisation methods to BM3D have been proposed [25–27], and much progress has been made in different aspects. However, these methods do not really improve two aspects of BM3D: time‐consumption and ineffectiveness in dealing with complex texture of an image.…”

Section: Related Wordmentioning

confidence: 99%

Improved BM3D denoising method

Jiangwei

Wang

2017

IET image process

View full text Add to dashboard Cite

Block matching 3D denoising (BM3D) is an excellent single‐image denoising method. However, it still needs to be improved for solving practical problems. In this study, the authors attempt to improve the method of BM3D. First, one of the problems of BM3D is that some of its references cannot perform self‐adaption when the noise intensity of the images is changed. Therefore, they propose a method using total variation (TV) to calculate the image noise intensity and make the references perform self‐adaption. Second, finding similar blocks in the BM3D method is a time‐consuming procedure. To solve this problem, they analyse the relationship between the numbers of similar blocks and denoising effect, improve the process of searching for similar blocks, and reduce the running time. Third, through the experiment they find that the denoising effect of BM3D method in the domain of complex texture is unsatisfactory. Thus, they proposed a hybrid denoising method for the complex texture area, using the new TV model and BM3D method together to restore the image. Their experimental results show that the improved BM3D method performs better than the original BM3D method.

show abstract

“…This section compares the algorithms proposed in this chapter with other algorithms, including t r a d i t i o n a l a l g o r i t h m s , s u c h a s t h e B M 3 D [5] denoising algorithm, and deep learning-based algorithms, such as the DnCNN algorithm [6] . For fair comparison, algorithms based on convolutional neural networks, such as SRCNN [7] , are trained on the training data set in this paper. In the following denoising simulation, Gaussian noise is added to the initial image, and then the denoising simulation is performed.…”

Section: Comparison With Other Methodsymentioning

confidence: 99%

A New Image Denoising Method with Gan Models

Huang¹

2020

JERA

View full text Add to dashboard Cite

In order to obtain clear images and solve the problems of low image quality caused by noise disturbance, a lot of researches have been done on image denoising techniques. In the theoretical system of algorithms studied so far, many algorithms can effectively remove noise in low-dimensional images, but at the same time, the results are slightly inferior when processing high-dimensional images. This paper proposes a q-GAN, which uses multi-scale in generating networks. The convolution kernel extracts image features and transforms the denoising problem into the feature domain. In the feature domain, a residual structure is used to denoise, and the noise distribution is removed from the feature distribution. There are residual noise features in the obtained denoising features, which are removed by subsequent feature filtering of the network structure, and finally a denoised image is generated by fusing the noiseless features.

show abstract

BM3D-based ultrasound image denoising via brushlet thresholding

Cited by 18 publications

References 12 publications

Automated classification of optical coherence tomography images of human atrial tissue

Automated classification of optical coherence tomography images of human atrial tissue

Improved BM3D denoising method

A New Image Denoising Method with Gan Models

Contact Info

Product

Resources

About