• 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

带金属伪影的工业计算机断层扫描的马尔可夫随机场分割。

Markov random field segmentation for industrial computed tomography with metal artefacts.

机构信息

Department of Industrial and Systems Engineering, IIT Kharagpur, India.

WMG, University of Warwick, UK.

出版信息

J Xray Sci Technol. 2018;26(4):573-591. doi: 10.3233/XST-17322.

DOI:10.3233/XST-17322
PMID:29562573
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC6130414/
Abstract

X-ray Computed Tomography (XCT) has become an important tool for industrial measurement and quality control through its ability to measure internal structures and volumetric defects. Segmentation of constituent materials in the volume acquired through XCT is one of the most critical factors that influence its robustness and repeatability. Highly attenuating materials such as steel can introduce artefacts in CT images that adversely affect the segmentation process, and results in large errors during quantification. This paper presents a Markov Random Field (MRF) segmentation method as a suitable approach for industrial samples with metal artefacts. The advantages of employing the MRF segmentation method are shown in comparison with Otsu thresholding on CT data from two industrial objects.

摘要

X 射线计算机断层扫描（XCT）通过测量内部结构和体积缺陷，已成为工业测量和质量控制的重要工具。在 XCT 获得的体积中对组成材料进行分割是影响其稳健性和可重复性的最关键因素之一。像钢这样的高衰减材料会在 CT 图像中引入伪影，从而对分割过程产生不利影响，并在定量过程中产生较大误差。本文提出了一种马尔可夫随机场（MRF）分割方法，作为一种适用于具有金属伪影的工业样本的方法。通过对两个工业物体的 CT 数据进行 Otsu 阈值处理和 MRF 分割方法的比较，展示了采用 MRF 分割方法的优势。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/e87977570c5b/xst-26-xst17322-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/24c32734d987/xst-26-xst17322-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/1d2113af5486/xst-26-xst17322-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/1757e56ee3ae/xst-26-xst17322-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/4df4babfbc22/xst-26-xst17322-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/ad4a8c2c05cf/xst-26-xst17322-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/2afbf9f9d86b/xst-26-xst17322-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/be44fb69bce8/xst-26-xst17322-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/86eb740ccec8/xst-26-xst17322-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/4529a973cf58/xst-26-xst17322-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/daf42b2ab125/xst-26-xst17322-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/9ac1f3e96a48/xst-26-xst17322-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/6832bac49cff/xst-26-xst17322-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/d17e590d57ee/xst-26-xst17322-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/2d6f39c8f291/xst-26-xst17322-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/f234a688d3ce/xst-26-xst17322-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/eefab6f107d0/xst-26-xst17322-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/772a9179560a/xst-26-xst17322-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/b4c1eb08bda3/xst-26-xst17322-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/f032f4564c33/xst-26-xst17322-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/e87977570c5b/xst-26-xst17322-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/24c32734d987/xst-26-xst17322-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/1d2113af5486/xst-26-xst17322-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/1757e56ee3ae/xst-26-xst17322-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/4df4babfbc22/xst-26-xst17322-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/ad4a8c2c05cf/xst-26-xst17322-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/2afbf9f9d86b/xst-26-xst17322-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/be44fb69bce8/xst-26-xst17322-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/86eb740ccec8/xst-26-xst17322-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/4529a973cf58/xst-26-xst17322-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/daf42b2ab125/xst-26-xst17322-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/9ac1f3e96a48/xst-26-xst17322-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/6832bac49cff/xst-26-xst17322-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/d17e590d57ee/xst-26-xst17322-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/2d6f39c8f291/xst-26-xst17322-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/f234a688d3ce/xst-26-xst17322-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/eefab6f107d0/xst-26-xst17322-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/772a9179560a/xst-26-xst17322-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/b4c1eb08bda3/xst-26-xst17322-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/f032f4564c33/xst-26-xst17322-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a01f/6130414/e87977570c5b/xst-26-xst17322-g020.jpg

相似文献

1
Markov random field segmentation for industrial computed tomography with metal artefacts.带金属伪影的工业计算机断层扫描的马尔可夫随机场分割。
J Xray Sci Technol. 2018;26(4):573-591. doi: 10.3233/XST-17322.
2
Development and validation of segmentation and interpolation techniques in sinograms for metal artifact suppression in CT.正弦图中金属伪影抑制的分割和插值技术的开发和验证。
Med Phys. 2010 Feb;37(2):620-8. doi: 10.1118/1.3276777.
3
A virtual sinogram method to reduce dental metallic implant artefacts in computed tomography-based attenuation correction for PET.一种用于在基于计算机断层扫描的正电子发射断层显像衰减校正中减少牙科金属植入物伪影的虚拟正弦图方法。
Nucl Med Commun. 2010 Jan;31(1):22-31. doi: 10.1097/MNM.0b013e32832fa241.
4
Semi-supervised segmentation of metal-artifact contaminated industrial CT images using improved CycleGAN.基于改进 CycleGAN 的工业 CT 金属伪影污染图像半监督分割。
J Xray Sci Technol. 2024;32(2):271-283. doi: 10.3233/XST-230233.
5
A segmentation of brain MRI images utilizing intensity and contextual information by Markov random field.利用马尔可夫随机场的强度和上下文信息对脑 MRI 图像进行分割。
Comput Assist Surg (Abingdon). 2017 Dec;22(sup1):200-211. doi: 10.1080/24699322.2017.1389398. Epub 2017 Oct 26.
6
Dual-energy-based metal segmentation for metal artifact reduction in dental computed tomography.基于能谱的牙科 CT 金属伪影校正中的金属分割。
Med Phys. 2018 Feb;45(2):714-724. doi: 10.1002/mp.12719. Epub 2018 Jan 2.
7
CT image crack segmentation method based on linear feature enhancement.基于线性特征增强的CT图像裂纹分割方法
J Xray Sci Technol. 2022;30(5):903-917. doi: 10.3233/XST-221171.
8
Reduction of metallic coil artefacts in computed tomography body imaging: effects of a new single-energy metal artefact reduction algorithm.计算机断层扫描身体成像中金属线圈伪影的减少：一种新型单能量金属伪影减少算法的效果
Eur Radiol. 2016 May;26(5):1378-86. doi: 10.1007/s00330-015-3950-6. Epub 2015 Aug 14.
9
Truncation compensation and metallic dental implant artefact reduction in PET/MRI attenuation correction using deep learning-based object completion.基于深度学习对象补全的 PET/MRI 衰减校正中截断补偿和金属牙种植体伪影减少。
Phys Med Biol. 2020 Sep 25;65(19):195002. doi: 10.1088/1361-6560/abb02c.
10
A Novel Method for Segmentation-Based Semiautomatic Quantitative Evaluation of Metal Artifact Reduction Algorithms.基于分割的新型半自动金属伪影降低算法定量评估方法。
Invest Radiol. 2019 Jun;54(6):365-373. doi: 10.1097/RLI.0000000000000549.

本文引用的文献

1
Modelling the penumbra in Computed Tomography1.在计算机断层扫描中对半暗带进行建模1。
J Xray Sci Technol. 2016 May 21;24(4):583-97. doi: 10.3233/XST-160576.
2
3D chemical imaging in the laboratory by hyperspectral X-ray computed tomography.实验室中通过高光谱X射线计算机断层扫描进行的3D化学成像。
Sci Rep. 2015 Oct 30;5:15979. doi: 10.1038/srep15979.
3
A prior-based metal artifact reduction algorithm for x-ray CT.一种用于X射线计算机断层扫描的基于先验的金属伪影减少算法。
J Xray Sci Technol. 2015;23(2):229-41. doi: 10.3233/XST-150483.
4
A simulation-based study on the influence of beam hardening in X-ray computed tomography for dimensional metrology.基于模拟的X射线计算机断层扫描中束硬化对尺寸计量影响的研究。
J Xray Sci Technol. 2015;23(1):65-82. doi: 10.3233/XST-140471.
5
Sparsity driven metal part reconstruction for artifact removal in dental CT.用于牙科CT伪影去除的稀疏驱动金属部件重建
J Xray Sci Technol. 2011;19(4):457-75. doi: 10.3233/XST-2011-0307.
6
Metal artifact reduction in CT by identifying missing data hidden in metals.利用金属中隐藏的缺失数据识别来减少 CT 中的金属伪影。
J Xray Sci Technol. 2013;21(3):357-72. doi: 10.3233/XST-130384.
7
An experimental survey of metal artefact reduction in computed tomography.金属伪影降低在计算机断层扫描中的实验性调查。
J Xray Sci Technol. 2013;21(2):193-226. doi: 10.3233/XST-130372.
8
CT metal artifact reduction method correcting for beam hardening and missing projections.CT 金属伪影降低方法，用于校正射束硬化和投影缺失。
Phys Med Biol. 2012 May 7;57(9):2803-18. doi: 10.1088/0031-9155/57/9/2803. Epub 2012 Apr 18.
9
Stochastic relaxation, gibbs distributions, and the bayesian restoration of images.随机松弛，吉布斯分布，以及贝叶斯图像恢复。
IEEE Trans Pattern Anal Mach Intell. 1984 Jun;6(6):721-41. doi: 10.1109/tpami.1984.4767596.
10
Modeling and segmentation of noisy and textured images using gibbs random fields.基于吉布斯随机场的噪声纹理图像建模与分割。
IEEE Trans Pattern Anal Mach Intell. 1987 Jan;9(1):39-55. doi: 10.1109/tpami.1987.4767871.