• 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

通过改进的全变差图像去噪方法在压缩感知磁共振成像重建中去除高密度高斯噪声

Removal of high density Gaussian noise in compressed sensing MRI reconstruction through modified total variation image denoising method.

作者信息

Zhu Yonggui, Shen Weiheng, Cheng Fanqiang, Jin Cong, Cao Gang

机构信息

School of Data Science and Media Intelligence, Communication University of China, Beijing, 100024, China.

School of Information and Communication Engineering, Communication University of China, Beijing, 100024, China.

出版信息

Heliyon. 2020 Mar 30;6(3):e03680. doi: 10.1016/j.heliyon.2020.e03680. eCollection 2020 Mar.

DOI:10.1016/j.heliyon.2020.e03680
PMID:32258499
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7113634/
Abstract

A modified total variation MRI image denoising method is proposed in this paper. First, the proposed method removes the noise in -space in compressed sensing MRI reconstruction. Then, the removed -space data is used as a partial frequency observation in compressed sensing MRI model. The proposed method shows better results than RecPF method, LDP method, TVCMRI method, and FCSA method in sparse MRI reconstruction. The proposed method is tested against Shepp-Logan phantom and real MR images corrupted by noise of different intensity level, and it gives better Signal-to-Noise Ratio (SNR), the relative error (ReErr), and the structural similarity (SSIM) than RecPF, LDP, TVCMRI, and FCSA.

摘要

本文提出了一种改进的全变差MRI图像去噪方法。首先，该方法在压缩感知MRI重建中去除空间噪声。然后，将去除的空间数据用作压缩感知MRI模型中的部分频率观测值。在稀疏MRI重建中，该方法比RecPF方法、LDP方法、TVCMRI方法和FCSA方法显示出更好的结果。该方法针对Shepp-Logan体模和受不同强度噪声干扰的真实MR图像进行了测试，并且在信噪比（SNR）、相对误差（ReErr）和结构相似性（SSIM）方面比RecPF、LDP、TVCMRI和FCSA表现更好。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/44c81215b9d2/gr010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/4f9ab7a3a0de/gr001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/44259b48629e/gr002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/0458d0022211/gr003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/a3b27a9cd402/gr004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/a1587082ced3/gr005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/bb922729fc86/gr006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/3a51405a67dd/gr007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/23eed105e3ae/gr008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/52b2d8d44e4e/gr009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/44c81215b9d2/gr010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/4f9ab7a3a0de/gr001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/44259b48629e/gr002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/0458d0022211/gr003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/a3b27a9cd402/gr004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/a1587082ced3/gr005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/bb922729fc86/gr006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/3a51405a67dd/gr007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/23eed105e3ae/gr008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/52b2d8d44e4e/gr009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/abdb/7113634/44c81215b9d2/gr010.jpg

相似文献

1
Removal of high density Gaussian noise in compressed sensing MRI reconstruction through modified total variation image denoising method.通过改进的全变差图像去噪方法在压缩感知磁共振成像重建中去除高密度高斯噪声
Heliyon. 2020 Mar 30;6(3):e03680. doi: 10.1016/j.heliyon.2020.e03680. eCollection 2020 Mar.
2
Retraction notice to "Removal of high density Gaussian noise in compressed sensing MRI reconstruction through modified total variation image denoising method" [Heliyon 6 (2020) e03680].撤稿通知：“通过改进的全变差图像去噪方法去除压缩感知磁共振成像重建中的高密度高斯噪声”[《Heliyon》6(2020)e03680]
Heliyon. 2025 Mar 18;11(8):e43202. doi: 10.1016/j.heliyon.2025.e43202. eCollection 2025 Mar 31.
3
MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting.基于残差移位的高效扩散概率模型的MRI超分辨率重建
Phys Med Biol. 2025 Jun 3. doi: 10.1088/1361-6560/ade049.
4
Compressed sensing based dynamic MR image reconstruction by using 3D-total generalized variation and tensor decomposition: k-t TGV-TD.基于三维全广义变分和张量分解的压缩感知动态磁共振图像重建：k-t TGV-TD。
BMC Med Imaging. 2022 May 27;22(1):101. doi: 10.1186/s12880-022-00826-1.
5
Aural toilet (ear cleaning) for chronic suppurative otitis media.慢性化脓性中耳炎的耳道清理（耳部清洁）
Cochrane Database Syst Rev. 2025 Jun 9;6(6):CD013057. doi: 10.1002/14651858.CD013057.pub3.
6
Generative priors for MRI reconstruction trained from magnitude-only images using phase augmentation.使用相位增强从仅幅度图像训练的用于磁共振成像重建的生成先验。
Philos Trans A Math Phys Eng Sci. 2025 Jun 19;383(2299):20240323. doi: 10.1098/rsta.2024.0323.
7
Validating a T1-weighted cine MRI for a 1.5T MR-Linac with temporal resolution appropriate for respiratory motion.验证适用于1.5T MR直线加速器的具有适合呼吸运动时间分辨率的T1加权电影磁共振成像。
Front Oncol. 2025 Jun 4;15:1575001. doi: 10.3389/fonc.2025.1575001. eCollection 2025.
8
Cauliflower leaf diseases: A computer vision dataset for smart agriculture.花椰菜叶部病害：一个用于智慧农业的计算机视觉数据集。
Data Brief. 2025 Apr 28;60:111594. doi: 10.1016/j.dib.2025.111594. eCollection 2025 Jun.
9
Molecular feature-based classification of retroperitoneal liposarcoma: a prospective cohort study.基于分子特征的腹膜后脂肪肉瘤分类：一项前瞻性队列研究。
Elife. 2025 May 23;14:RP100887. doi: 10.7554/eLife.100887.
10
Automated Multi-grade Brain Tumor Classification Using Adaptive Hierarchical Optimized Horse Herd BiLSTM Fusion Network in MRI Images.基于自适应分层优化马群双向长短期记忆融合网络的MRI图像自动多分级脑肿瘤分类
Interdiscip Sci. 2025 Jun 18. doi: 10.1007/s12539-025-00708-4.

引用本文的文献

1
Continuum topological derivative - a novel application tool for denoising CT and MRI medical images.连续拓扑导数——一种用于 CT 和 MRI 医学图像去噪的新应用工具。
BMC Med Imaging. 2024 Jul 24;24(1):182. doi: 10.1186/s12880-024-01341-1.
2
An optical multiple-image authentication based on computational ghost imaging and total-variation minimization.一种基于计算鬼成像和全变差最小化的光学多重图像认证方法。
Heliyon. 2023 Jun 29;9(7):e17682. doi: 10.1016/j.heliyon.2023.e17682. eCollection 2023 Jul.
3
Perceptually Motivated Generative Model for Magnetic Resonance Image Denoising.

本文引用的文献

1
An efficient algorithm for dynamic MRI using low-rank and total variation regularizations.基于低秩和全变差正则化的动态 MRI 高效算法。
Med Image Anal. 2018 Feb;44:14-27. doi: 10.1016/j.media.2017.11.003. Epub 2017 Nov 17.
2
Hybrid CS-DMRI: Periodic Time-Variant Subsampling and Omnidirectional Total Variation Based Reconstruction.混合 CS-DMRI：基于周期性时变欠采样和全方向总变分的重建。
IEEE Trans Med Imaging. 2017 Oct;36(10):2148-2159. doi: 10.1109/TMI.2017.2717502. Epub 2017 Jun 20.
3
Non-Stationary Rician Noise Estimation in Parallel MRI Using a Single Image: A Variance-Stabilizing Approach.
基于感知的磁共振图像去噪生成模型。
J Digit Imaging. 2023 Apr;36(2):725-738. doi: 10.1007/s10278-022-00744-2. Epub 2022 Dec 6.
4
Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images.结合学习增强的抗噪声深度卷积神经网络用于在噪声X射线图像中检测新冠肺炎
J Comput Sci. 2022 Sep;63:101763. doi: 10.1016/j.jocs.2022.101763. Epub 2022 Jul 7.
5
Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images.基于噪声和去噪数据的学习增强策略：提高深度卷积神经网络在 X 射线图像中 COVID-19 检测的泛化能力。
Comput Biol Med. 2021 Sep;136:104704. doi: 10.1016/j.compbiomed.2021.104704. Epub 2021 Jul 29.
基于单幅图像的并行 MRI 中非平稳 Rice 噪声估计：一种方差稳定化方法。
IEEE Trans Pattern Anal Mach Intell. 2017 Oct;39(10):2015-2029. doi: 10.1109/TPAMI.2016.2625789. Epub 2016 Nov 7.
4
Dynamic MR image reconstruction-separation from undersampled (k,t)-space via low-rank plus sparse prior.基于低秩稀疏先验的欠采（k，t）空间磁共振图像重建-分离。
IEEE Trans Med Imaging. 2014 Aug;33(8):1689-701. doi: 10.1109/TMI.2014.2321190. Epub 2014 Apr 30.
5
Generalized total variation-based MRI Rician denoising model with spatially adaptive regularization parameters.具有空间自适应正则化参数的基于广义全变差的MRI莱斯噪声去噪模型。
Magn Reson Imaging. 2014 Jul;32(6):702-20. doi: 10.1016/j.mri.2014.03.004. Epub 2014 Mar 18.
6
Multi-structural signal recovery for biomedical compressive sensing.多结构信号的生物医学压缩感知恢复。
IEEE Trans Biomed Eng. 2013 Oct;60(10):2794-805. doi: 10.1109/TBME.2013.2264772. Epub 2013 May 23.
7
Efficient improvements on the BDND filtering algorithm for the removal of high-density impulse noise.高效改进 BDND 滤波算法以去除高密度脉冲噪声。
IEEE Trans Image Process. 2013 Mar;22(3):1223-32. doi: 10.1109/TIP.2012.2228496. Epub 2012 Nov 20.
8
Efficient MR image reconstruction for compressed MR imaging.基于压缩感知的高效磁共振图像重建。
Med Image Anal. 2011 Oct;15(5):670-9. doi: 10.1016/j.media.2011.06.001. Epub 2011 Jun 24.
9
Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems.用于约束全变差图像去噪和去模糊问题的基于快速梯度的算法。
IEEE Trans Image Process. 2009 Nov;18(11):2419-34. doi: 10.1109/TIP.2009.2028250. Epub 2009 Jul 24.
10
Sparse MRI: The application of compressed sensing for rapid MR imaging.稀疏磁共振成像：压缩感知在快速磁共振成像中的应用。
Magn Reson Med. 2007 Dec;58(6):1182-95. doi: 10.1002/mrm.21391.