Shape Based Speckle Removal for Ultrasound Image Segmentation

doi:10.1109/ICIP.2019.8803493

Citations

PDF

Open Access

More filters

Proceedings Article•DOI•

A New Hybrid filtering technique for Despeckling of Ultrasound Images

[...]

Shivam Kumar Pal¹, Ankur Bhardwai¹, Anand Prakash Shukla¹•Institutions (1)

Krishna Institute of Engineering and Technology¹

03 Sep 2021

TL;DR: In this article, a comparison of existing speckle reduction strategies was carried out in comparison of simulated photos to compare the results, and the hybrid filter was found to have equivalent enactment and hence functions well concluded a wide series of noise variation.

...read moreread less

Abstract: Medical diagnostics can benefit from ultrasound (US) imaging. Because it is non-invasive and inexpensive, the US is recommended over other medical diagnosis techniques. The inclusion of speckle noise in US images reduces the utility of the images. Correct diagnosis can be aided by a technology that eliminates speckle noise in US images. While reducing the speckle noise, our approach should preserve the critical structural figures cutting-edge US images. The method used for this work can reduce speckle noise in denoised image while still preserving structural information. The suggested method successfully denoises synthetic and real ultrasound pictures, as evidenced by the consequences of numerous measurable tests and optical review. A comparison of existing speckle reduction strategies was carried out in this study. We compared anistropic diffusion, Frost diffusion, Lee, and the Hmedian filter. The approaches are initially tested on simulated photos to compare the results. Exponential thresholding outperforms the other strategies when the noise variance is bigger. Furthermore, the hybrid filter is found to have equivalent enactment and hence functions well concluded a wide series of noise variation.

...read moreread less

References

PDF

Open Access

More filters

Journal Article•DOI•

A threshold selection method from gray level histograms

[...]

Nobuyuki Otsu

01 Jan 1979-IEEE Transactions on Systems, Man, and Cybernetics

37,017 citations

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

...The proposed denoising and segmentation using [13] on 240 × 400 ultrasound image takes∼ 6 secs in a 16 GB Dell Precision 3....
[...]
...At the minimum value of (γ3/γ2), the final segmentation is performed by applying [13] on the speckle reduced image obtained in step (f) above....
[...]
...1: Noise removal and segmentation (using [13]) in real (row 1) and phantom (row 2) datasets....
[...]
...In order to minimize (2), first we perform segmentation on I(n) (partial denoised image after n iterations) using [13]....
[...]

Journal Article•DOI•

Scale-space and edge detection using anisotropic diffusion

[...]

Pietro Perona¹, Jitendra Malik¹•Institutions (1)

University of California, Berkeley¹

01 Jul 1990-IEEE Transactions on Pattern Analysis and Machine Intelligence

TL;DR: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.

...read moreread less

Abstract: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interregion smoothing. It is shown that the 'no new maxima should be generated at coarse scales' property of conventional scale space is preserved. As the region boundaries in the approach remain sharp, a high-quality edge detector which successfully exploits global information is obtained. Experimental results are shown on a number of images. Parallel hardware implementations are made feasible because the algorithm involves elementary, local operations replicated over the image. >

...read moreread less

12,560 citations

"Shape Based Speckle Removal for Ult..." refers background in this paper

...One existing approach to speckle reduction updates partial differential equations in the form of anisotropic diffusion to smooth homogeneous regions while preserving boundaries [5, 8, 9]....
[...]

Journal Article•DOI•

Speckle reducing anisotropic diffusion

[...]

Yongjian Yu¹, Scott T. Acton¹•Institutions (1)

University of Virginia¹

01 Nov 2002-IEEE Transactions on Image Processing

TL;DR: This paper provides the derivation of speckle reducing anisotropic diffusion (SRAD), a diffusion method tailored to ultrasonic and radar imaging applications, and validates the new algorithm using both synthetic and real linear scan ultrasonic imagery of the carotid artery.

...read moreread less

Abstract: This paper provides the derivation of speckle reducing anisotropic diffusion (SRAD), a diffusion method tailored to ultrasonic and radar imaging applications. SRAD is the edge-sensitive diffusion for speckled images, in the same way that conventional anisotropic diffusion is the edge-sensitive diffusion for images corrupted with additive noise. We first show that the Lee and Frost filters can be cast as partial differential equations, and then we derive SRAD by allowing edge-sensitive anisotropic diffusion within this context. Just as the Lee (1980, 1981, 1986) and Frost (1982) filters utilize the coefficient of variation in adaptive filtering, SRAD exploits the instantaneous coefficient of variation, which is shown to be a function of the local gradient magnitude and Laplacian operators. We validate the new algorithm using both synthetic and real linear scan ultrasonic imagery of the carotid artery. We also demonstrate the algorithm performance with real SAR data. The performance measures obtained by means of computer simulation of carotid artery images are compared with three existing speckle reduction schemes. In the presence of speckle noise, speckle reducing anisotropic diffusion excels over the traditional speckle removal filters and over the conventional anisotropic diffusion method in terms of mean preservation, variance reduction, and edge localization.

...read moreread less

1,816 citations

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

...OSRAD is similar to SRAD except for a modified diffusion which performs different amount of smoothing along the direction of maximum curvature and other directions....
[...]
...This speckle reducing anisotropic diffusion (SRAD) approach is based on local image features (the local presence or absence of boundaries) and ignores topology on a global level....
[...]
...For SRAD [5], we have chosen 400 iterations with 0....
[...]
...For SRAD [5], we have chosen 400 iterations with 0.02 as the smoothing time step....
[...]
...This filter is called oriented SRAD (OSRAD)....
[...]

Proceedings Article•DOI•

Image smoothing via L0 gradient minimization

[...]

Li Xu¹, Cewu Lu¹, Yi Xu¹, Jiaya Jia¹•Institutions (1)

The Chinese University of Hong Kong¹

12 Dec 2011

TL;DR: This work presents a new image editing method, particularly effective for sharpening major edges by increasing the steepness of transition while eliminating a manageable degree of low-amplitude structures in an optimization framework making use of L0 gradient minimization.

...read moreread less

Abstract: We present a new image editing method, particularly effective for sharpening major edges by increasing the steepness of transition while eliminating a manageable degree of low-amplitude structures. The seemingly contradictive effect is achieved in an optimization framework making use of L0 gradient minimization, which can globally control how many non-zero gradients are resulted in to approximate prominent structure in a sparsity-control manner. Unlike other edge-preserving smoothing approaches, our method does not depend on local features, but instead globally locates important edges. It, as a fundamental tool, finds many applications and is particularly beneficial to edge extraction, clip-art JPEG artifact removal, and non-photorealistic effect generation.

...read moreread less

919 citations

Journal Article•DOI•

Speckle analysis and smoothing of synthetic aperture radar images

[...]

Jong-Sen Lee¹•Institutions (1)

United States Naval Research Laboratory¹

01 Sep 1981-Computer Graphics and Image Processing

TL;DR: This paper develops a statistical technique to define a noise model, and then successfully applies a local statistics noise filtering algorithm to a set of actual SEASAT SAR images, resulting in smoothed images that permit observers to resolve fine detail with an enhanced edge effect.

...read moreread less

880 citations

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

...The values of vesselness measure in Table 3 show that SBSR yields a segmentation from which better vessels can be reconstructed compared to [4], [5] or [6]....
[...]
...For Lee filter [4] we have used 5x5 masks for averaging with 0....
[...]
...One of the most basic and widely used methods is found in the Lee filter [4]....
[...]
...We compare the performance of SBSR with a number of speckle removing filters, namely: Lee filter [4], SRAD [5], DPAD [6] and [12]....
[...]

Shape Based Speckle Removal for Ultrasound Image Segmentation

Citations

References

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

"Shape Based Speckle Removal for Ult..." refers background in this paper

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

"Shape Based Speckle Removal for Ult..." refers background or methods in this paper

Related Papers (5)