Multi-scale ultrasound image denoising algorithm based on deep learning model for super-resolution reconstruction
Pages 6 - 11
Abstract
Effective suppression of speckle noise in ultrasound images is of great significance for improving image quality and clinical diagnostic analysis. The traditional edge enhancement nonlinear coherent diffusion (EENCD) and multi-scale filtering based on pyramid transformation are not obvious enough for the subtle features after the image is denoised. Since the super-resolution deep learning model SRGAN can restore more realistic texture details of the image, this attempt is made to improve the traditional Laplace pyramid, and the 2x magnification factor reconstruction image of the SRGAN model is used to replace the upsampling of the Laplace pyramid reconstruction stage, and the EENCD method is still used on the Laplace pyramid to suppress the image speckle. By comparing this method with the traditional method in the simulation image and the real ultrasound image, the experimental results show that the proposed method is superior to the original algorithm in terms of structure, edge protection and noise suppression.
References
[1]
Sagheer S V M, George S N. A review on medical image denoising algorithms[J]. Biomedical signal processing and control, 2020, 61: 102036.https://doi.org/10.1016/j.bspc.2020.102036
[2]
Zhang G, Song R, Ding B, Laplacian pyramid based non-linear coherence diffusion for real-time ultrasound image speckle reduction[J]. Applied Acoustics, 2021, 183: 108298.https://doi.org/10.1016/j.apacoust.2021.108298
[3]
Chang C C, Hsiao J Y, Hsieh C P. An adaptive median filter for image denoising[C]//2008 Second international symposium on intelligent information technology application. IEEE, 2008, 2: 346-350.
[4]
Balocco S, Gatta C, Pujol O, SRBF: Speckle reducing bilateral filtering[J]. Ultrasound in medicine & biology, 2010, 36(8): 1353-1363.https://doi.org/10.1016/j.ultrasmedbio.2010.05.007
[5]
Li Z, Yu L, Trzasko J D, Adaptive nonlocal means filtering based on local noise level for CT denoising[J]. Medical physics, 2014, 41(1): 011908.https://doi.org/10.1118/1.4851635
[6]
Yu Y, Acton S T. Speckle reducing anisotropic diffusion[J]. IEEE Transactions on image processing, 2002, 11(11): 1260-1270.
[7]
Abd-Elmoniem K Z, Youssef A B M, Kadah Y M. Real-time speckle redu-ction and coherence enhancement in ultrasound imaging via nonlinear anis-otropic diffusion[J]. IEEE Transactions on Biomedical Engineering, 2002, 49(9): 997-1014.
[8]
Zhang F, Yoo Y M, Koh L M, Nonlinear diffusion in Laplacian pyramid domain for ultrasonic speckle reduction[J]. IEEE Transactions on Medical Imaging, 2007, 26(2): 200-211.
[9]
Kim B S, Kim J S, Song H J. Ultrasound speckle reduction and edge en-hancing in Laplacian pyramid[C]//2010 5th Cairo International Biomedical Engineering Conference. IEEE, 2010: 37-40.
[10]
Ledig C, Theis L, Huszár F, Photo-realistic single image super resol-ution using a generative adversarial network[C]//Proceedings of the IEEE c-onference on computer vision and pattern recognition. 2017: 4681-4690.
[11]
Kang J, Lee J Y, Yoo Y. A new feature-enhanced speckle reduction metho-d based on multiscale analysis for ultrasound b-mode imaging[J]. IEEE Tr-ansactions on Biomedical Engineering, 2015, 63(6): 1178-1191.
[12]
Geetha R V, Kalaivani S. Laplacian Pyramid based Speckle Reducing Anisotropic Diffusion (LPSRAD) for SAR Images[J]. International Journal of Applied Engineering Research, 10(30): 2015.
[13]
He K, Zhang X, Ren S, Deep residual learning for image recognitio-n[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[14]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[15]
Dabov K, Foi A, Katkovnik V, Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Transactions on image processing, 2007, 16(8): 2080-2095.
[16]
Yamaya H, Mimura Y, Yamazaki H, 2Pa5-1 Image Quality Assessment of 3D Ultrasound Images Based on SSIM[C]//Proceedings of Symposium on Ultrasonic Electronics. Institute for Ultrasonic Elecronics, 2021, 42: 2Pa5-1.https://doi.org/10.24492/use.42.0_2Pa5-1
[17]
Zhang L, Zhang L, Mou X, FSIM: A feature similarity index for i-mage quality assessment[J]. IEEE transactions on Image Processing, 2011, 20(8): 2378-2386.
[18]
Sun Y, Xin Z, Huang X, Overview of SAR image denoising based on transform domain[M]//3D Imaging Technologies—Multi-dimensional Signal Processing and Deep Learning. Springer, Singapore, 2021: 39-47.
[19]
Singh P, Diwakar M. Total variation‐based ultrasound image despeckling using method noise thresholding in non‐subsampled contourlet transform[J]. International Journal of Imaging Systems and Technology, 2023. https://doi.org/10.1002/ima.22851
Index Terms
- Multi-scale ultrasound image denoising algorithm based on deep learning model for super-resolution reconstruction
Index terms have been assigned to the content through auto-classification.
Recommendations
Super resolution reconstruction algorithm of video image based on deep self encoding learning
Super resolution reconstruction of video image is a research hotspot in the field of image processing, and it is widely used in video surveillance, image processing, criminal analysis and other fields. Super resolution image reconstruction can ...
Modified sparse representation based image super-resolution reconstruction method
To improve the geometric structure and texture features of reconstructed images, a novel image super-resolution reconstruction (ISR) method based on modified sparse representation, here denoted by MSR_ISR, is discussed in this paper. In this algorithm, ...
Effective Use of Low Resolution Images for Super-Resolution Reconstruction
CISP '08: Proceedings of the 2008 Congress on Image and Signal Processing, Vol. 3 - Volume 03High resolution image reconstruction is a powerful image processing techniques which sought to obtain a high resolution image from observed multiple low resolution images. High resolution image reconstruction is very useful in various areas such as ...
Comments
Information & Contributors
Information
Published In
August 2023
215 pages
ISBN:9798400708190
DOI:10.1145/3622896
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 03 October 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CCRIS 2023
CCRIS 2023: 2023 4th International Conference on Control, Robotics and Intelligent System
August 25 - 27, 2023
Guangzhou, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 39Total Downloads
- Downloads (Last 12 months)39
- Downloads (Last 6 weeks)3
Reflects downloads up to 18 Aug 2024
Other Metrics
Citations
Cited By
View allView Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format