• 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

基于有界广义高斯混合模型的医学图像配准算法

Medical Image Registration Algorithm Based on Bounded Generalized Gaussian Mixture Model.

作者信息

Wang Jingkun, Xiang Kun, Chen Kuo, Liu Rui, Ni Ruifeng, Zhu Hao, Xiong Yan

机构信息

Department of Orthopaedics, Daping Hospital, Army Medical University, Chongqing, China.

College of Automation, Chongqing University of Posts and Telecommunications, Chongqing, China.

出版信息

Front Neurosci. 2022 Jun 2;16:911957. doi: 10.3389/fnins.2022.911957. eCollection 2022.

DOI:10.3389/fnins.2022.911957
PMID:35720703
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9201218/
Abstract

In this paper, a method for medical image registration based on the bounded generalized Gaussian mixture model is proposed. The bounded generalized Gaussian mixture model is used to approach the joint intensity of source medical images. The mixture model is formulated based on a maximum likelihood framework, and is solved by an expectation-maximization algorithm. The registration performance of the proposed approach on different medical images is verified through extensive computer simulations. Empirical findings confirm that the proposed approach is significantly better than other conventional ones.

摘要

本文提出了一种基于有界广义高斯混合模型的医学图像配准方法。有界广义高斯混合模型用于逼近源医学图像的联合强度。该混合模型基于最大似然框架构建，并通过期望最大化算法求解。通过大量的计算机模拟验证了所提方法在不同医学图像上的配准性能。实证结果证实，所提方法明显优于其他传统方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/e65d031ad4be/fnins-16-911957-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/b5163a9607de/fnins-16-911957-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/6d7b28d57d5a/fnins-16-911957-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/221d532c12b7/fnins-16-911957-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/bb49f14f3dd7/fnins-16-911957-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/6770488b0684/fnins-16-911957-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/1053455c7d00/fnins-16-911957-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/e65d031ad4be/fnins-16-911957-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/b5163a9607de/fnins-16-911957-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/6d7b28d57d5a/fnins-16-911957-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/221d532c12b7/fnins-16-911957-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/bb49f14f3dd7/fnins-16-911957-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/6770488b0684/fnins-16-911957-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/1053455c7d00/fnins-16-911957-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5de9/9201218/e65d031ad4be/fnins-16-911957-g007.jpg

相似文献

1
Medical Image Registration Algorithm Based on Bounded Generalized Gaussian Mixture Model.基于有界广义高斯混合模型的医学图像配准算法
Front Neurosci. 2022 Jun 2;16:911957. doi: 10.3389/fnins.2022.911957. eCollection 2022.
2
Retinal image registration via feature-guided Gaussian mixture model.基于特征引导高斯混合模型的视网膜图像配准
J Opt Soc Am A Opt Image Sci Vis. 2016 Jul 1;33(7):1267-76. doi: 10.1364/JOSAA.33.001267.
3
An innovative multimodal/multispectral image registration method for medical images based on the Expectation-Maximization algorithm.一种基于期望最大化算法的创新型医学图像多模态/多光谱图像配准方法。
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:5223-6. doi: 10.1109/EMBC.2015.7319569.
4
A transformation-based approach to Gaussian mixture density estimation for bounded data.一种用于有界数据的基于变换的高斯混合密度估计方法。
Biom J. 2019 Jul;61(4):873-888. doi: 10.1002/bimj.201800174. Epub 2019 Apr 14.
5
Bayesian pixel classification using spatially variant finite mixtures and the generalized EM algorithm.使用空间可变有限混合模型和广义期望最大化算法的贝叶斯像素分类
IEEE Trans Image Process. 1998;7(7):1014-28. doi: 10.1109/83.701161.
6
Robust Non-Rigid Feature Matching for Image Registration Using Geometry Preserving.使用几何保持的鲁棒非刚性特征匹配用于图像配准
Sensors (Basel). 2019 Jun 18;19(12):2729. doi: 10.3390/s19122729.
7
Robust generative asymmetric GMM for brain MR image segmentation.用于脑部磁共振图像分割的稳健生成式非对称高斯混合模型
Comput Methods Programs Biomed. 2017 Nov;151:123-138. doi: 10.1016/j.cmpb.2017.08.017. Epub 2017 Aug 24.
8
A Bayesian bounded asymmetric mixture model with segmentation application.带分段应用的贝叶斯有界非对称混合模型。
IEEE J Biomed Health Inform. 2014 Jan;18(1):109-19. doi: 10.1109/JBHI.2013.2264749.
9
A Rough Set Bounded Spatially Constrained Asymmetric Gaussian Mixture Model for Image Segmentation.一种用于图像分割的粗糙集有界空间约束非对称高斯混合模型
PLoS One. 2017 Jan 3;12(1):e0168449. doi: 10.1371/journal.pone.0168449. eCollection 2017.
10
Attraction-repulsion expectation-maximization algorithm for image reconstruction and sensor field estimation.用于图像重建和传感器场估计的吸引-排斥期望最大化算法
IEEE Trans Image Process. 2009 Sep;18(9):2004-11. doi: 10.1109/TIP.2009.2024574. Epub 2009 Jun 5.

本文引用的文献

1
Accurate MR Image Registration to Anatomical Reference Space for Diffuse Glioma.将弥散性胶质瘤的磁共振图像精确配准到解剖学参考空间
Front Neurosci. 2020 Jun 5;14:585. doi: 10.3389/fnins.2020.00585. eCollection 2020.
2
Robust Non-Rigid Feature Matching for Image Registration Using Geometry Preserving.使用几何保持的鲁棒非刚性特征匹配用于图像配准
Sensors (Basel). 2019 Jun 18;19(12):2729. doi: 10.3390/s19122729.
3
Predicting CT Image From MRI Data Through Feature Matching With Learned Nonlinear Local Descriptors.通过基于学习的非线性局部描述符的特征匹配来从 MRI 数据预测 CT 图像。
IEEE Trans Med Imaging. 2018 Apr;37(4):977-987. doi: 10.1109/TMI.2018.2790962.
4
MIND Demons: Symmetric Diffeomorphic Deformable Registration of MR and CT for Image-Guided Spine Surgery.MIND 恶魔：用于图像引导脊柱手术的磁共振成像与计算机断层扫描的对称微分同胚可变形配准
IEEE Trans Med Imaging. 2016 Nov;35(11):2413-2424. doi: 10.1109/TMI.2016.2576360. Epub 2016 Jun 2.
5
Confidence Estimation for Medical Image Registration Based On Stereo Confidences.基于立体置信度的医学图像配准置信度估计
IEEE Trans Med Imaging. 2016 Feb;35(2):539-49. doi: 10.1109/TMI.2015.2481609. Epub 2015 Sep 25.
6
A Digital Preclinical PET/MRI Insert and Initial Results.数字临床前 PET/MRI 插件及初步结果。
IEEE Trans Med Imaging. 2015 Nov;34(11):2258-70. doi: 10.1109/TMI.2015.2427993. Epub 2015 Apr 29.
7
Deformable medical image registration: a survey.可变形医学图像配准：综述。
IEEE Trans Med Imaging. 2013 Jul;32(7):1153-90. doi: 10.1109/TMI.2013.2265603. Epub 2013 May 31.
8
Second-order optimization of mutual information for real-time image registration.基于互信息的实时图像配准二阶优化。
IEEE Trans Image Process. 2012 Sep;21(9):4190-203. doi: 10.1109/TIP.2012.2199124. Epub 2012 May 11.
9
Registering a multisensor ensemble of images.注册一个多传感器图像集成。
IEEE Trans Image Process. 2010 May;19(5):1236-47. doi: 10.1109/TIP.2009.2039371. Epub 2009 Dec 28.
10
Parametric image alignment using enhanced correlation coefficient maximization.使用增强相关系数最大化的参数图像对齐
IEEE Trans Pattern Anal Mach Intell. 2008 Oct;30(10):1858-65. doi: 10.1109/TPAMI.2008.113.