Edge Preserved Speckle Noise Reduction Using Integrated Fuzzy Filters

Biradar, Nagashettappa; Dewal, M. L.; Rohit, Manoj Kumar

doi:10.1155/2014/876434

Cited by 17 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main reason is the coherent nature of the ultrasound image acquisition process [5]. Multiplicative noise is more problematic than additive noise since it is not amenable to simple linear filtering [6]. There is little doubt that despeckling ultrasound images would enhance the performance of image classifiers such as our CNNs.…”

mentioning

confidence: 99%

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Fast and accurate segmentation of musculoskeletal ultrasound images is an on-going challenge. Two principal factors make this task difficult: firstly, the presence of speckle noise arising from the interference that accompanies all coherent imaging approaches; secondly, the sometimes subtle interaction between musculoskeletal components that leads to non-uniformity of the image intensity. Our work presents an investigation of the potential of Convolutional Neural Networks (CNNs) to address both of these problems. CNNs are an effective tool that has previously been used in image processing of several biomedical imaging modalities. However, there is little published material addressing the processing of musculoskeletal ultrasound images, particularly using a panoramic technique. In our work we explore the effectiveness of CNNs when trained to act as a pre-segmentation pixel classifier that determines whether a pixel is an edge or non-edge pixel. Our CNNs are trained using two different ground truth interpretations. The first one uses an automatic Canny edge detector to provide the ground truth image; in the second interpretation, the ground truth was obtained using the same image marked-up by an expert anatomist. In this initial study the CNNs have been trained using half of the prepared data from one image, using the other half for testing; validation was also carried out using three unseen ultrasound images. CNN performance was assessed using Mathew's Correlation Coefficient, Sensitivity, Specificity and Accuracy. The results show that CNN performance when using expert ground truth image is better than in the case of using Canny ground truth image. Our technique is promising and has the potential to speed-up the image processing pipeline using appropriately trained CNNs.

show abstract

mentioning

confidence: 99%

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Jabbar

Day

Heinz

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…The selection of parameters for each filter is based on the available discussions in research papers [5,7À9,18] and experiments results presented by authors of this paper in [20,41,46]. Table 6 and for TTE images in Tables 7À9.…”

Section: Resultsmentioning

confidence: 99%

“…The log operation decouples the multiplicative components into independent individual noise-free and noise components [2,5,6,20]. Filters such as DPAD [17], generalized likelihood estimation method (GLM) [28], NLM [39], PPB [40], and anisotropic TV (ATV) [19] are implemented using the multiplicative noise model and all other filters [6][7][8][9][20][21][22][23][24][25][26]34,41,42,46,47] are implemented using log transformation of the input image.…”

Section: Despeckling Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Speckle Noise Reduction in B-Mode Echocardiographic Images: A comparison

Biradar

Dewal

Rohit

2015

IETE Technical Review

Self Cite

View full text Add to dashboard Cite

This paper presents the despeckling applications of 48 filters for B-mode echocardiographic images. The filters are grouped into eight types, namely, local statistics, fuzzy, Fourier, multiscale, nonlinear iterative, total variation, nonlocal mean, and hybrid. The thrust areas of analyses are noise suppression, edge, and structure preservation evaluated in terms of image quality metrics, visual quality assessment, and clinical validation. The comparative analysis reveals that filters based on generalized likelihood ratio, local statistics (mean and variance), detail preserving anisotropic diffusion, fast bilateral, sparse representation based beta process factor analysis, and patch-based locally optimal Wiener and probabilistic nonlocal means stand out among the techniques being considered for comparison.

show abstract

“…Fuzzy logic is powerful tool because of its ability to deal with complex image processing problems [18]. Fuzzy rules describe quantitative relation between variables in linguistic terms.…”

Section: B Fuzzy Rule Based Diffusivitymentioning

confidence: 99%

Fuzzy Based Adaptive Anisotropic Diffusion Despeckling Filter

Bannulmath*,

Havaldar

2019

IJITEE

View full text Add to dashboard Cite

Echocardiography is an ultrasound of the heart for the assessment of cardiac structure and function. Images obtained from the ultrasound suffer from a speckle Noise. Speckle is an inherent multiplicative noise which affects the visual perception by discriminating the fine details in the echocardiography. Speckle removal is important step to improve the visual quality of the echocardiography for better diagnosis. Anisotropic diffusion is one of the popular techniques to despeckle the ultrasound image in recent times. In this paper, we propose a fuzzy based adaptive anisotropic diffusion despeckling filter to despeckle echocardiography ultrasound image. The results show that fuzzy diffusion when combined with adaptive anisotropic diffusion filter gives better performance compared with existing despeckling filters

show abstract

Edge Preserved Speckle Noise Reduction Using Integrated Fuzzy Filters

Cited by 17 publications

References 31 publications

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

Speckle Noise Reduction in B-Mode Echocardiographic Images: A comparison

Fuzzy Based Adaptive Anisotropic Diffusion Despeckling Filter

Contact Info

Product

Resources

About