X-ray image denoising using blind source separation in anscombe domain

Fan SHEN; Han-lin LI; Bin SUN

doi:10.3788/OPE.20202801.0244

您当前的位置：

首页 >

文章列表页 >

X-ray image denoising using blind source separation in anscombe domain

Information Sciences | 更新时间：2020-08-13

- X-ray image denoising using blind source separation in anscombe domain
- Optics and Precision Engineering Vol. 28, Issue 1, Pages: 244-250(2020)
- 作者机构：
  
  1.南京邮电大学电子与光学工程学院、微电子学院，江苏南京 210023；
  2.南京邮电大学自动化学院，江苏南京 210023
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20202801.0244
  CLC： TP391.41
- Received：08 July 2019，
  
  Accepted：29 August 2019，
  
  Published：25 January 2020
- 稿件说明：
移动端阅览
Fan SHEN, Han-lin LI, Bin SUN. X-ray image denoising using blind source separation in anscombe domain[J]. Optics and precision engineering, 2020, 28(1): 244-250.
DOI：

Fan SHEN, Han-lin LI, Bin SUN. X-ray image denoising using blind source separation in anscombe domain[J]. Optics and precision engineering, 2020, 28(1): 244-250. DOI： 10.3788/OPE.20202801.0244.

摘要

为降低泊松噪声对X射线图像质量的影响，本研究提出一种采用非线性主分量分析(NLPCA)对X射线图像序列进行盲源分离的降噪方法。该降噪方法首先采样一序列X射线图像，并通过Anscombe变换将图像中泊松噪声转化为高斯噪声；然后将每张含噪声图像视为噪声分量和信号分量的组合，进而采用NLPCA将信号分量和噪声分量分离达到降噪目的；最后通过Anscombe逆变换获取最终降噪图像。研究结果表明：当序列中含噪声图像张数从2增加到50时，提出的降噪方法可以将Shepp-Logan头模型含噪声图像的PSNR值由28.289 4 dB提高到37.267 8 dB、SSIM值由0.700 7提高到0.963 8。相比较常用的降噪算法，提出的降噪方法在有效消除X射线图像中泊松噪声的同时，使图像中细节轮廓保留更完整。

Abstract

To remove the Poisson noise from the X-ray images

in this paper

it was proposed that noise was reduced by using Nonlinear Principal Component Analysis (NLPCA) from the X-ray image sequence. At first

an X-ray image sequence was sampled and the Poisson noise in images was converted into Gaussian noise through Anscombe transform; every noisy image was regarded as a combination of the noise components and the signal component

and then NLPCA was used to separate the signal component from the noise components to reduce noise; the final denoised image was obtained by using Anscombe inverse transform. The results show that

when the number of noisy images in the sequence increases from 2 to 50

the proposed denoising method increases the noisy Shepp-Logan image's PSNR value from 28.289 4 dB to 37.267 8 dB and increases the SSIM value from 0.700 7 to 0.963 8. Compared with other denoising methods

the proposed denoising method can preserve more image details while reducing the Poisson noise.

关键词

Keywords

references

KANG E, MIN J, YE J C. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction[J]. Medical Physics , 2017, 44(10): 360-375.

WANG C, YANG J. Poisson noise removal of images on graphs using tight wavelet frames[J]. The Visual Computer , 2017, 34(10): 1357-5369.

费彬, 孙京阳, 张俊举, 等.基于稀疏处理的多能X射线分离成像[J].光学精密工程, 2017, 25(4): 574-579.

FEI B, SUN J Y, ZHANG J J, et al .. Separation of multi-energy X-ray imaging based on sparse processing[J]. Opt. Precision Eng., 2017, 25(4): 574-579. (in Chinese).

SELESNICK IW, SENDUR L. Bicariate shrinkage functions for wavelet-based denoising exploiting interscale dependency[J]. IEEE Transactions on signal processing , 2002, 50(11): 2744-2756.

骆乐, 吴长强, 林杰, 等.基于光子计数激光雷达的时域去噪[J].光学精密工程, 2018, 26(5): 1175-1180.

LUO L, WU CH Q, LIN J, et al .. Time-domain denoising based on photon-counting LiDAR[J]. Opt. Precision Eng ., 2018, 26(5): 1175-1180. (in Chinese).

MA L, MOISAN L, YU J, et al .. A dictionary learning approach for poisson image deblurring[J]. IEEE Transactions on Medical Imaging , 2013, 32(7): 1277-1289.

孙京阳, 喻春雨, 董仕佳.非局部均值噪声预测的独立成分分析降噪研究[J].光学精密工程, 2018, 26(2): 511-516.

SUN J Y, YU CH Y, DONG SH J, et al .. Noise reduction of independent component analysis based on NLmeans noise prediction[J]. Opt. Precision Eng. , 2018, 26(2): 511-516. (in Chinese).

MANDUCA A, YU L, TRZASKO J D, et al .. Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT[J]. Medical Physics , 2009, 36(11): 4911-4919.

毕一鸣, 马建华, 刘楠, 等.基于Anscombe变换域BM3D滤波的低剂量CT重建[J].计算机工程与应用, 2010, 46(13): 216-220.

BI Y M, MA J H, LIU N, et al .. Anscombe transform and BM3D filtering based projection restoration for low-does CT Reconstruction[J]. Computer Engineering and Applications , 2010, 46(13): 216-220. (in Chinese).

张倩颖, 谢晓振.加权Schatten范数低秩表示的高光谱图像恢复[J].光学精密工程, 2019, 27(2): 421-432.

ZHANG Q Y, XIE X ZH. Hyperspectral image restoration via weighted Schatten norm low-rank representation[J]. Opt. Precision Eng ., 2019, 27(2): 421-432.(in Chinese).

REVELL L J, KLAUS S, EUGENIO V, et al .. Graphs in phylogenetic comparative analysis: Anscombe's quartet revisited[J]. Methods in Ecology and Evolution , 2018, 9(10): 2145-2154.

BORGES L R, AZZARI L, BAKIC P R, et al .. Restoration of low-dose digital breast tomosynthesis[J]. Measurement Science and Technology , 2018, 29(6): 064003.

GROTAS S, YAKOBY Y, GERA I, et al .. Power systems topology and state estimation by graph blind source separation[J]. IEEE Transactions On Signal Processing , 2018, 67(8): 2036-2051.

戚佳佳, 顾国华, 陈远金, 等.基于贝叶斯自适应估计的光子计数集成成像[J].光学精密工程, 2018, 26(3): 565-571.

QI J J, GU G H, CHEN Y J, et al .. Photon counting integral imaging based on adaptive Bayesian estimation[J]. Opt. Precision Eng. , 2018, 26(3): 565-571.(in Chinese).

FENG P, WANG W, NAQVI S M, et al .. Adaptive retrodiction particle phd filter for multiple human tracking[J]. IEEE Signal Processing Letters , 2016, 23(11): 1592-1596.

GRANIC A, DAVIES K, MARTIN-RUIZ C, et al .. Grip strength and inflammatory biomarker profiles in very old adults[J]. Age and Ageing , 2017, 46(6): 976-982.

王迪, 司玉娟, 刘通, 等.基于主成分分析进行特征融合的心拍分类[J].光学精密工程, 2015, 23(10): 453-458.

WANG D, SI Y J, LIU T, et al .. Heart beat classification based on feature fusion by principle component analysis[J]. Opt. Precision Eng ., 2015, 23(10): 453-458. (in Chinese).

QI H L, ZHOU L H, XU Y, et al .. A Bayesian-map method based on TV for CT image reconstruction from sparse and limited data[J]. Chinese Journal of Biomedical Engineering , 2017, 26(2): 82-88.

YU C Y, LI Y, FEI B, et al .. Blind source separation based x-ray image denoising from an image sequence[J]. Review of Scientific Instruments , 2015, 86(9): 093701.

Views

319

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

DRT Net： dual Res-Transformer pneumonia recognition model oriented to feature enhancement

Adaptive brightness correction of dim-lightening color images

Denoising method of micro-focus X-ray images corrupted with mixed multiplicative and additive noises

X-ray automatic inspection techniques for carbon product defects

Related Author

LU Huiling

ZHOU Tao

PENG Caiyue

DU Yuhu

DANG Pei

LIU Fengzhen

Gang CHEN

Yan LIU

Related Institution

College of Computer Science and Engineering， North Minzu University

Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission， North Minzu University

School of Medical Information & Engineering， Ningxia Medical University

Nanjing Univ Posts & Telecommun，College of Electronic and Optical Engineering & College of Microelectronics

Nanjing Univ Posts & Telecommun， School of Automation

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰