快速射频振荡:使用深度学习加速7T MRI中的射频振荡

Zhengyi Lu , Hao Liang , Ming Lu , Xiao Wang , Xinqiang Yan , Yuankai Huo
{"title":"快速射频振荡:使用深度学习加速7T MRI中的射频振荡","authors":"Zhengyi Lu ,&nbsp;Hao Liang ,&nbsp;Ming Lu ,&nbsp;Xiao Wang ,&nbsp;Xinqiang Yan ,&nbsp;Yuankai Huo","doi":"10.1016/j.metrad.2025.100166","DOIUrl":null,"url":null,"abstract":"<div><div>Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field <span><math><mrow><mo>(</mo><mrow><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></mrow><mo>)</mo></mrow></math></span> inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields. Next, we train a Residual Network (ResNet) to map <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.</div></div>","PeriodicalId":100921,"journal":{"name":"Meta-Radiology","volume":"3 3","pages":"Article 100166"},"PeriodicalIF":0.0000,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning\",\"authors\":\"Zhengyi Lu ,&nbsp;Hao Liang ,&nbsp;Ming Lu ,&nbsp;Xiao Wang ,&nbsp;Xinqiang Yan ,&nbsp;Yuankai Huo\",\"doi\":\"10.1016/j.metrad.2025.100166\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field <span><math><mrow><mo>(</mo><mrow><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></mrow><mo>)</mo></mrow></math></span> inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields. Next, we train a Residual Network (ResNet) to map <span><math><msubsup><mrow><mi>B</mi></mrow><mrow><mn>1</mn></mrow><mrow><mo>+</mo></mrow></msubsup></math></span> fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.</div></div>\",\"PeriodicalId\":100921,\"journal\":{\"name\":\"Meta-Radiology\",\"volume\":\"3 3\",\"pages\":\"Article 100166\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Meta-Radiology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2950162825000347\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Meta-Radiology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2950162825000347","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

超高场(UHF)磁共振成像(MRI)提供了更高的信噪比(SNR),实现了极高的空间分辨率,有利于临床诊断和高级研究。然而,向更高场的跳跃带来了复杂性,特别是发射射频(RF)场(B1+)的不均匀性,表现为不均匀的翻转角度和图像强度不规则。这些伪影会降低图像质量,阻碍临床应用。传统的射频振荡方法,如最小二乘(MLS)优化,可以有效地缓解B1+非均匀性,但仍然耗时。最近的机器学习方法,包括迭代投影岭回归的RF Shim预测和其他深度学习架构,提出了替代途径。尽管这些方法显示出了希望,但挑战仍然存在,例如长时间的训练、有限的网络复杂性和实际数据需求。在本文中,我们引入了一种称为Fast-RF-Shimming的基于整体学习的框架,与传统的MLS方法相比,该框架的速度提高了5000倍。在初始阶段,我们采用随机初始化的自适应矩估计(Adam)从多通道B1+场中获得所需的参考振荡权值。接下来,我们训练一个残差网络(ResNet)将B1+场直接映射到最终的射频振荡输出,并将置信度参数纳入其损失函数。最后,我们设计了非均匀场检测器(NFD),这是一个可选的后处理步骤,以确保识别极端的非均匀结果。与标准MLS优化的比较评估强调了处理速度和预测精度的显着提高,这表明我们的技术在解决持续非同质性挑战方面显示了一个有希望的解决方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning
Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field (B1+) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate B1+ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel B1+ fields. Next, we train a Residual Network (ResNet) to map B1+ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信