Robust Cardiac Motion Estimation With Dictionary Learning and Temporal Regularization for Ultrasound Imaging

N. Ouzir, J. Bioucas-Dias, A. Basarab, J. Tourneret
{"title":"Robust Cardiac Motion Estimation With Dictionary Learning and Temporal Regularization for Ultrasound Imaging","authors":"N. Ouzir, J. Bioucas-Dias, A. Basarab, J. Tourneret","doi":"10.1109/ULTSYM.2019.8925936","DOIUrl":null,"url":null,"abstract":"Estimating the cardiac motion from ultrasound (US) images is an ill-posed problem that requires regularization. In a recent study, it was shown that constraining the cardiac motion fields to be patch-wise sparse in a learnt overcomplete motion dictionary is more accurate than local parametric models (affine) or global functions (B-splines, total variation). In this work, we extend this method by incorporating temporal smoothness in a multi-frame optical-flow (OF) strategy. An efficient optimization strategy using the constrained split augmented Lagrangian shrinkage algorithm (C-SALSA) is proposed. The performance is evaluated on a realistic simulated cardiac dataset with available ground-truth. A comparison with the pairwise approach shows the interest of the proposed temporal regularization and multi-frame strategy in terms of accuracy and computational time.","PeriodicalId":6759,"journal":{"name":"2019 IEEE International Ultrasonics Symposium (IUS)","volume":"13 1-2 1","pages":"2326-2329"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE International Ultrasonics Symposium (IUS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ULTSYM.2019.8925936","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Estimating the cardiac motion from ultrasound (US) images is an ill-posed problem that requires regularization. In a recent study, it was shown that constraining the cardiac motion fields to be patch-wise sparse in a learnt overcomplete motion dictionary is more accurate than local parametric models (affine) or global functions (B-splines, total variation). In this work, we extend this method by incorporating temporal smoothness in a multi-frame optical-flow (OF) strategy. An efficient optimization strategy using the constrained split augmented Lagrangian shrinkage algorithm (C-SALSA) is proposed. The performance is evaluated on a realistic simulated cardiac dataset with available ground-truth. A comparison with the pairwise approach shows the interest of the proposed temporal regularization and multi-frame strategy in terms of accuracy and computational time.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于字典学习和时间正则化的超声成像鲁棒心脏运动估计
从超声图像估计心脏运动是一个需要正则化的病态问题。在最近的一项研究中,研究表明,在学习的过完备运动字典中,将心脏运动场约束为斑块稀疏比局部参数模型(仿射)或全局函数(b样条,总变分)更准确。在这项工作中,我们通过在多帧光流(OF)策略中加入时间平滑性来扩展该方法。提出了一种基于约束分割增广拉格朗日收缩算法(C-SALSA)的优化策略。在一个真实的模拟心脏数据集上评估了该性能。与两两方法的比较显示了所提出的时间正则化和多帧策略在精度和计算时间方面的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Development of a 1-D Linear Phased Ultrasonic Array for Intravascular Sonoporation Growth, Properties, and Applications of Al1-xScxN Thin Films Measurement of Thrombolysis Enhanced by EkoSonic Catheter-Based Endovascular Therapy Power Switching Noise Removal in Sensitive Doppler Applications A Hydrogel Glove for Emergency Ultrasound Screening
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1