• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

非对称卷积神经网络（NSCT）域中低剂量X射线图像的泊松-高斯噪声分析与估计

Poisson-Gaussian Noise Analysis and Estimation for Low-Dose X-ray Images in the NSCT Domain.

作者信息

Lee Sangyoon, Lee Min Seok, Kang Moon Gi

机构信息

School of Electrical and Electronics Engineering, Yonsei University, 50 Yonsei-Ro, Seodaemun-Gu, Seoul 03722, Korea.

出版信息

Sensors (Basel). 2018 Mar 29;18(4):1019. doi: 10.3390/s18041019.

DOI:10.3390/s18041019
PMID:29596335
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5948630/
Abstract

The noise distribution of images obtained by X-ray sensors in low-dosage situations can be analyzed using the Poisson and Gaussian mixture model. Multiscale conversion is one of the most popular noise reduction methods used in recent years. Estimation of the noise distribution of each subband in the multiscale domain is the most important factor in performing noise reduction, with non-subsampled contourlet transform (NSCT) representing an effective method for scale and direction decomposition. In this study, we use artificially generated noise to analyze and estimate the Poisson-Gaussian noise of low-dose X-ray images in the NSCT domain. The noise distribution of the subband coefficients is analyzed using the noiseless low-band coefficients and the variance of the noisy subband coefficients. The noise-after-transform also follows a Poisson-Gaussian distribution, and the relationship between the noise parameters of the subband and the full-band image is identified. We then analyze noise of actual images to validate the theoretical analysis. Comparison of the proposed noise estimation method with an existing noise reduction method confirms that the proposed method outperforms traditional methods.

摘要

利用泊松和高斯混合模型可以分析低剂量情况下X射线传感器所获图像的噪声分布。多尺度变换是近年来最常用的降噪方法之一。多尺度域中各子带噪声分布的估计是进行降噪的最重要因素，非下采样轮廓波变换（NSCT）是一种有效的尺度和方向分解方法。在本研究中，我们使用人工生成的噪声来分析和估计NSCT域中低剂量X射线图像的泊松-高斯噪声。利用无噪声的低频带系数和有噪声子带系数的方差来分析子带系数的噪声分布。变换后的噪声也服从泊松-高斯分布，并确定了子带与全波段图像噪声参数之间的关系。然后，我们分析实际图像的噪声以验证理论分析。将所提出的噪声估计方法与现有的降噪方法进行比较，证实了所提出的方法优于传统方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/d894f7070313/sensors-18-01019-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/915d786c96f0/sensors-18-01019-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/3cb6ec11bf47/sensors-18-01019-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/88a34bf54196/sensors-18-01019-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/f15a624c9ab4/sensors-18-01019-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/e439e0d7584b/sensors-18-01019-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/ea5b66e82627/sensors-18-01019-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/13d511cb9c17/sensors-18-01019-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/a355e44f6ffa/sensors-18-01019-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/526948402cf5/sensors-18-01019-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/abc14adc11b2/sensors-18-01019-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/d24eb590bcdc/sensors-18-01019-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/1371c648aafb/sensors-18-01019-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/a7f89d9e0c91/sensors-18-01019-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/6ca4a441a67d/sensors-18-01019-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/9b9fe4eeeb79/sensors-18-01019-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/bfa6fc761550/sensors-18-01019-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/d894f7070313/sensors-18-01019-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/915d786c96f0/sensors-18-01019-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/3cb6ec11bf47/sensors-18-01019-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/88a34bf54196/sensors-18-01019-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/f15a624c9ab4/sensors-18-01019-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/e439e0d7584b/sensors-18-01019-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/ea5b66e82627/sensors-18-01019-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/13d511cb9c17/sensors-18-01019-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/a355e44f6ffa/sensors-18-01019-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/526948402cf5/sensors-18-01019-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/abc14adc11b2/sensors-18-01019-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/d24eb590bcdc/sensors-18-01019-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/1371c648aafb/sensors-18-01019-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/a7f89d9e0c91/sensors-18-01019-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/6ca4a441a67d/sensors-18-01019-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/9b9fe4eeeb79/sensors-18-01019-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/bfa6fc761550/sensors-18-01019-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e3ad/5948630/d894f7070313/sensors-18-01019-g017.jpg

相似文献

1
Poisson-Gaussian Noise Analysis and Estimation for Low-Dose X-ray Images in the NSCT Domain.非对称卷积神经网络（NSCT）域中低剂量X射线图像的泊松-高斯噪声分析与估计
Sensors (Basel). 2018 Mar 29;18(4):1019. doi: 10.3390/s18041019.
2
Poisson-Gaussian Noise Reduction Using the Hidden Markov Model in Contourlet Domain for Fluorescence Microscopy Images.基于轮廓波域隐马尔可夫模型的泊松-高斯噪声去除用于荧光显微镜图像
PLoS One. 2015 Sep 9;10(9):e0136964. doi: 10.1371/journal.pone.0136964. eCollection 2015.
3
Remote Sensing Image Change Detection Based on NSCT-HMT Model and Its Application.基于NSCT-HMT模型的遥感影像变化检测及其应用
Sensors (Basel). 2017 Jun 6;17(6):1295. doi: 10.3390/s17061295.
4
Fusion of Unmanned Aerial Vehicle Panchromatic and Hyperspectral Images Combining Joint Skewness-Kurtosis Figures and a Non-Subsampled Contourlet Transform.结合联合偏度峰度图和非下采样轮廓波变换的无人飞行器全色与高光谱图像融合。
Sensors (Basel). 2018 Oct 15;18(10):3467. doi: 10.3390/s18103467.
5
Choosing the filter for catenary image enhancement method based on the non-subsampled contourlet transform.基于非下采样轮廓波变换的悬链线图像增强方法中滤波器的选择。
Rev Sci Instrum. 2017 May;88(5):054701. doi: 10.1063/1.4983375.
6
Denoising of polychromatic CT images based on their own noise properties.基于多色CT图像自身噪声特性的去噪处理。
Med Phys. 2016 May;43(5):2251. doi: 10.1118/1.4945022.
7
Medical Image Fusion Based on Sparse Representation and PCNN in NSCT Domain.基于非下采样Contourlet变换（NSCT）域中稀疏表示和脉冲耦合神经网络（PCNN）的医学图像融合
Comput Math Methods Med. 2018 May 24;2018:2806047. doi: 10.1155/2018/2806047. eCollection 2018.
8
Method of Improved Fuzzy Contrast Combined Adaptive Threshold in NSCT for Medical Image Enhancement.非下采样Contourlet变换中改进的模糊对比度联合自适应阈值医学图像增强方法
Biomed Res Int. 2017;2017:3969152. doi: 10.1155/2017/3969152. Epub 2017 Jun 28.
9
Improved image fusion method based on NSCT and accelerated NMF.基于 NSCT 和加速 NMF 的改进图像融合方法。
Sensors (Basel). 2012;12(5):5872-87. doi: 10.3390/s120505872. Epub 2012 May 7.
10
Image denoising in mixed Poisson-Gaussian noise.混合泊松-高斯噪声下的图像去噪。
IEEE Trans Image Process. 2011 Mar;20(3):696-708. doi: 10.1109/TIP.2010.2073477. Epub 2010 Sep 13.

引用本文的文献

1
Optimization Method to Predict Optimal Noise Reduction Parameters for the Non-Local Means Algorithm Based on the Scintillator Thickness in Radiography.基于放射成像中闪烁体厚度预测非局部均值算法最优降噪参数的优化方法
Sensors (Basel). 2023 Dec 13;23(24):9803. doi: 10.3390/s23249803.
2
Pulmonary abnormality screening on chest x-rays from different machine specifications: a generalized AI-based image manipulation pipeline.不同机型胸片肺部异常筛查：基于 AI 的通用图像操作流程。
Eur Radiol Exp. 2023 Nov 9;7(1):68. doi: 10.1186/s41747-023-00386-1.
3
Development of Adaptive Point-Spread Function Estimation Method in Various Scintillation Detector Thickness for X-ray Imaging.

本文引用的文献

1
X-ray fluoroscopy noise modeling for filter design.X 射线荧光透视噪声建模用于滤波器设计。
Int J Comput Assist Radiol Surg. 2013 Mar;8(2):269-78. doi: 10.1007/s11548-012-0772-8. Epub 2012 Jun 21.
2
Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise.广义 Anscombe 变换对泊松-高斯噪声的最优反演。
IEEE Trans Image Process. 2013 Jan;22(1):91-103. doi: 10.1109/TIP.2012.2202675. Epub 2012 Jun 5.
3
Image denoising in mixed Poisson-Gaussian noise.混合泊松-高斯噪声下的图像去噪。
用于X射线成像的不同闪烁探测器厚度下自适应点扩散函数估计方法的开发
Sensors (Basel). 2023 Sep 30;23(19):8185. doi: 10.3390/s23198185.
4
Early assessment of lung function in coronavirus patients using invariant markers from chest X-rays images.利用胸部 X 光图像中的不变特征标志物对冠状病毒患者的肺功能进行早期评估。
Sci Rep. 2021 Jun 8;11(1):12095. doi: 10.1038/s41598-021-91305-0.
5
Toward a priori noise characterization for real-time edge-aware denoising in fluoroscopic devices.针对荧光透视设备中实时边缘感知去噪的先验噪声特征化。
Biomed Eng Online. 2021 Apr 7;20(1):36. doi: 10.1186/s12938-021-00874-8.
6
A novel perceptual two layer image fusion using deep learning for imbalanced COVID-19 dataset.一种用于不平衡新冠肺炎数据集的基于深度学习的新型感知双层图像融合方法。
PeerJ Comput Sci. 2021 Feb 10;7:e364. doi: 10.7717/peerj-cs.364. eCollection 2021.
7
Effectiveness of Non-Local Means Algorithm with an Industrial 3 MeV LINAC High-Energy X-Ray System for Non-Destructive Testing.非局部均值算法在工业3兆电子伏特直线加速器高能X射线系统无损检测中的有效性
Sensors (Basel). 2020 May 5;20(9):2634. doi: 10.3390/s20092634.
8
Noise Estimation for Image Sensor Based on Local Entropy and Median Absolute Deviation.基于局部熵和中值绝对偏差的图像传感器噪声估计。
Sensors (Basel). 2019 Jan 16;19(2):339. doi: 10.3390/s19020339.
9
A Multiscale Denoising Framework Using Detection Theory with Application to Images from CMOS/CCD Sensors.基于检测理论的多尺度去噪框架及其在 CMOS/CCD 传感器图像中的应用。
Sensors (Basel). 2019 Jan 8;19(1):206. doi: 10.3390/s19010206.
IEEE Trans Image Process. 2011 Mar;20(3):696-708. doi: 10.1109/TIP.2010.2073477. Epub 2010 Sep 13.
4
Image modeling and denoising with orientation-adapted Gaussian scale mixtures.基于方向自适应高斯尺度混合模型的图像建模与去噪
IEEE Trans Image Process. 2008 Nov;17(11):2089-101. doi: 10.1109/tip.2008.2004796.
5
Practical Poissonian-Gaussian noise modeling and fitting for single-image raw-data.用于单图像原始数据的实用泊松高斯噪声建模与拟合
IEEE Trans Image Process. 2008 Oct;17(10):1737-54. doi: 10.1109/TIP.2008.2001399.
6
Image coding using wavelet transform.基于小波变换的图像编码。
IEEE Trans Image Process. 1992;1(2):205-20. doi: 10.1109/83.136597.
7
Image denoising using scale mixtures of Gaussians in the wavelet domain.在小波域中使用高斯尺度混合进行图像去噪。
IEEE Trans Image Process. 2003;12(11):1338-51. doi: 10.1109/TIP.2003.818640.
8
The curvelet transform for image denoising.用于图像去噪的曲波变换。
IEEE Trans Image Process. 2002;11(6):670-84. doi: 10.1109/TIP.2002.1014998.
9
An EM algorithm for wavelet-based image restoration.一种基于小波的图像恢复的期望最大化算法。
IEEE Trans Image Process. 2003;12(8):906-16. doi: 10.1109/TIP.2003.814255.
10
The finite ridgelet transform for image representation.用于图像表示的有限脊波变换。
IEEE Trans Image Process. 2003;12(1):16-28. doi: 10.1109/TIP.2002.806252.