ABSTRACT
In order to effectively improve the speckle noise suppression ability and preserve edge structure information in medical ultrasound images, an edge enhancement method based on Bayesian Non-Local Means and Convolution Neural Network is proposed in this paper. Firstly, the method performs smoothing filtering based on Bayesian Non-Local Means. And then introduces Local Laplacian Filter to enhance edge of the denoised image to improve the edge preservation ability. Finally, the edge-enhanced images and the speckle noise images as dataset to train Convolutional Neural Network denoising model. The experimental results demonstrate that the proposed method is superior to the traditional denoising algorithms that is compared in both speckle noise suppression and edge information retention.
- Goyal B, Dogra A, Agrawal S, Image denoising review: From classical to state-of-the-art approaches[J]. Information fusion, 2020, 55: 220-244.Google Scholar
- Fu Xiaowei, Yang Xuefei, Chen Fang, An adaptive medical ultrasound images despeckling method based on deep learning [J]. Journal of Electronics & Information Technology, 2020, 42(07): 1782-1789.Google Scholar
- Sagheer S V M, George S N. A review on medical image denoising algorithms[J]. Biomedical signal processing and control, 2020, 61: 102036.Google Scholar
- Hao Z C, Hong J S. UWB bandpass filter using cascaded miniature high-pass and low-pass filters with multilayer liquid crystal polymer technology[J]. IEEE Transactions on microwave theory and techniques, 2010, 58(4): 941-948.Google ScholarCross Ref
- Zhang J, Lin G, Wu L, Speckle filtering of medical ultrasonic images using wavelet and guided filter[J]. Ultrasonics, 2016, 65: 177-193.Google ScholarCross Ref
- Yongjian Y and Acton S T . Speckle reducing anisotropic diffusion, Image Processing[J]. IEEE Transactions on Image Processing, 2002, 11(11):1260-1270.Google ScholarDigital Library
- Buades A, Coll B, Morel J M. A non-local algorithm for image denoising[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). San Diego, CA, USA: IEEE, 2005: 60-65.Google Scholar
- Dabov K, Foi A, Katkovnik V, Image denoising with block-matching and 3D filtering[J]. Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, 2006, 6064: 354-365.Google Scholar
- Coupé P, Hellier P, Kervrann C, Nonlocal means-based speckle filtering for ultrasound images[J]. IEEE transactions on image processing, 2009, 18(10): 2221-2229.Google ScholarDigital Library
- Wang Y, Ge X, Ma H, Deep learning in medical ultrasound image analysis: a review[J]. IEEE Access, 2021, 9: 54310-54324.Google ScholarCross Ref
- Chen J, Chen J, Chao H, Image blind denoising with generative adversarial network based noise modeling[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA: IEEE, 2018: 3155-3164.Google Scholar
- Zhang K, Zuo W, Chen Y, Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising[J]. IEEE transactions on image processing, 2017, 26(7): 3142-3155.Google Scholar
- Zheng Yuanyue, Xu Mingen, Wang Ling. Improved weighted non-local mean ultrasonic image denoising[J]. Journal of Image and Graphics, 2017, 22(06): 778-786.Google Scholar
- Zhou Y, Zang H, Xu S, An iterative speckle filtering algorithm for ultrasound images based on Bayesian nonlocal means filter model[J]. Biomedical Signal Processing and Control, 2019, 48: 104-117.Google ScholarCross Ref
- Paris S, Hasinoff S W, Kautz J. Local Laplacian filters: Edge-aware image processing with a Laplacian pyramid[J]. ACM Trans. Graph., 2011, 30(4): 68.Google ScholarDigital Library
- Sumiya Y, Otsuka T, Maeda Y, Gaussian Fourier Pyramid for Local Laplacian Filter[J]. IEEE Signal Processing Letters, 2021, 29: 11-15.Google ScholarCross Ref
- Zhang Huijuan, Zhang Damin, Yan Wei, Wavelet transform image denoising algorithm based on improved threshold function [J]. Application Research of Computers, 2020, 37(5): 1545-1548.Google Scholar
- Xiong Chengchen, Jiang Weili, Jian Lizhong, Noise reduction model of medical ultrasound images based on dual attention mechanism[J]. Laser & Optoelectronics Progress, 2022, 59(02):411-420.Google Scholar
- Ultrasound image edge enhancement method based on Bayesian Non-Local Means and Convolution Neural Network
Recommendations
Performance Enhancement and Analysis of Filters in Ultrasound Image Denoising
AbstractImage denoising could be a major concern within the field of medical imaging. An ultrasound is also referred to as ultrasonography, which is a device that is used to create images of the inner body by using high frequency sound waves. Ultrasound ...
Local statistics and non-local mean filter for speckle noise reduction in medical ultrasound image
Medical ultrasound images are corrupted by speckle noise, which is multiplicative. This noise limits the contrast resolution in these images and complicates image-based quantitative measurement and diagnosis. In this study, the speckle noise in the ...
SAR Speckle Reduction Based on Nonlocal Means Method
ICCMS '10: Proceedings of the 2010 Second International Conference on Computer Modeling and Simulation - Volume 02Synthetic aperture radar (SAR) images are inherently affected by speckle noise, which is due to the coherent nature of the scattering phenomenon. This paper presents a novel SAR speckle reduction method base on nonlocal means (NLM) filter. NLM is ...
Comments