利用物理引导神经网络对神经流体的四维流磁共振成像进行超分辨率和去噪。

IF 3 2区 医学 Q3 ENGINEERING, BIOMEDICAL
Neal M Patel, Emily R Bartusiak, Sean M Rothenberger, A J Schwichtenberg, Edward J Delp, Vitaliy L Rayz
{"title":"利用物理引导神经网络对神经流体的四维流磁共振成像进行超分辨率和去噪。","authors":"Neal M Patel, Emily R Bartusiak, Sean M Rothenberger, A J Schwichtenberg, Edward J Delp, Vitaliy L Rayz","doi":"10.1007/s10439-024-03606-w","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To obtain high-resolution velocity fields of cerebrospinal fluid (CSF) and cerebral blood flow by applying a physics-guided neural network (div-mDCSRN-Flow) to 4D flow MRI.</p><p><strong>Methods: </strong>The div-mDCSRN-Flow network was developed to improve spatial resolution and denoise 4D flow MRI. The network was trained with patches of paired high-resolution and low-resolution synthetic 4D flow MRI data derived from computational fluid dynamic simulations of CSF flow within the cerebral ventricles of five healthy cases and five Alzheimer's disease cases. The loss function combined mean squared error with a binary cross-entropy term for segmentation and a divergence-based regularization term for the conservation of mass. Performance was assessed using synthetic 4D flow MRI in one healthy and one Alzheimer' disease cases, an in vitro study of healthy cerebral ventricles, and in vivo 4D flow imaging of CSF as well as flow in arterial and venous blood vessels. Comparison was performed to trilinear interpolation, divergence-free radial basis functions, divergence-free wavelets, 4DFlowNet, and our network without divergence constraints.</p><p><strong>Results: </strong>The proposed network div-mDCSRN-Flow outperformed other methods in reconstructing high-resolution velocity fields from synthetic 4D flow MRI in healthy and AD cases. The div-mDCSRN-Flow network reduced error by 22.5% relative to linear interpolation for in vitro core voxels and by 49.5% in edge voxels.</p><p><strong>Conclusion: </strong>The results demonstrate generalizability of our 4D flow MRI super-resolution and denoising approach due to network training using flow patches and physics-based constraints. The mDCSRN-Flow network can facilitate MRI studies involving CSF flow measurements in cerebral ventricles and association of MRI-based flow metrics with cerebrovascular health.</p>","PeriodicalId":7986,"journal":{"name":"Annals of Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks.\",\"authors\":\"Neal M Patel, Emily R Bartusiak, Sean M Rothenberger, A J Schwichtenberg, Edward J Delp, Vitaliy L Rayz\",\"doi\":\"10.1007/s10439-024-03606-w\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>To obtain high-resolution velocity fields of cerebrospinal fluid (CSF) and cerebral blood flow by applying a physics-guided neural network (div-mDCSRN-Flow) to 4D flow MRI.</p><p><strong>Methods: </strong>The div-mDCSRN-Flow network was developed to improve spatial resolution and denoise 4D flow MRI. The network was trained with patches of paired high-resolution and low-resolution synthetic 4D flow MRI data derived from computational fluid dynamic simulations of CSF flow within the cerebral ventricles of five healthy cases and five Alzheimer's disease cases. The loss function combined mean squared error with a binary cross-entropy term for segmentation and a divergence-based regularization term for the conservation of mass. Performance was assessed using synthetic 4D flow MRI in one healthy and one Alzheimer' disease cases, an in vitro study of healthy cerebral ventricles, and in vivo 4D flow imaging of CSF as well as flow in arterial and venous blood vessels. Comparison was performed to trilinear interpolation, divergence-free radial basis functions, divergence-free wavelets, 4DFlowNet, and our network without divergence constraints.</p><p><strong>Results: </strong>The proposed network div-mDCSRN-Flow outperformed other methods in reconstructing high-resolution velocity fields from synthetic 4D flow MRI in healthy and AD cases. The div-mDCSRN-Flow network reduced error by 22.5% relative to linear interpolation for in vitro core voxels and by 49.5% in edge voxels.</p><p><strong>Conclusion: </strong>The results demonstrate generalizability of our 4D flow MRI super-resolution and denoising approach due to network training using flow patches and physics-based constraints. The mDCSRN-Flow network can facilitate MRI studies involving CSF flow measurements in cerebral ventricles and association of MRI-based flow metrics with cerebrovascular health.</p>\",\"PeriodicalId\":7986,\"journal\":{\"name\":\"Annals of Biomedical Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of Biomedical Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s10439-024-03606-w\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Biomedical Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10439-024-03606-w","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

摘要

目的:通过将物理引导神经网络(div-mDCSRN-Flow)应用于四维血流磁共振成像,获得高分辨率的脑脊液(CSF)和脑血流速度场:div-mDCSRN-Flow 网络是为提高空间分辨率和去噪 4D 血流 MRI 而开发的。该网络使用从五例健康病例和五例阿尔茨海默病病例脑室内 CSF 流动的计算流体动力学模拟中获得的成对高分辨率和低分辨率合成 4D 流量 MRI 数据片段进行训练。损失函数结合了用于分割的均方误差和二元交叉熵项,以及用于质量守恒的基于发散的正则化项。使用合成的 4D 流量 MRI 评估了一个健康病例和一个阿尔茨海默病病例的性能、健康脑室的体外研究、CSF 的体内 4D 流量成像以及动脉和静脉血管中的流量。与三线性插值、无发散径向基函数、无发散小波、4DFlowNet 和我们的无发散约束网络进行了比较:结果:在根据健康和注意力缺失症病例的合成四维血流磁共振成像重建高分辨率速度场方面,提议的网络 div-mDCSRN-Flow 优于其他方法。div-mDCSRN-Flow 网络与线性插值法相比,体外核心体素的误差减少了 22.5%,边缘体素的误差减少了 49.5%:结果表明,我们的四维血流磁共振成像超分辨率和去噪方法具有通用性,这得益于使用血流补丁和基于物理的约束条件进行的网络训练。mDCSRN-Flow 网络可促进涉及脑室 CSF 流量测量的磁共振成像研究,并将基于磁共振成像的流量指标与脑血管健康联系起来。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks.

Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks.

Purpose: To obtain high-resolution velocity fields of cerebrospinal fluid (CSF) and cerebral blood flow by applying a physics-guided neural network (div-mDCSRN-Flow) to 4D flow MRI.

Methods: The div-mDCSRN-Flow network was developed to improve spatial resolution and denoise 4D flow MRI. The network was trained with patches of paired high-resolution and low-resolution synthetic 4D flow MRI data derived from computational fluid dynamic simulations of CSF flow within the cerebral ventricles of five healthy cases and five Alzheimer's disease cases. The loss function combined mean squared error with a binary cross-entropy term for segmentation and a divergence-based regularization term for the conservation of mass. Performance was assessed using synthetic 4D flow MRI in one healthy and one Alzheimer' disease cases, an in vitro study of healthy cerebral ventricles, and in vivo 4D flow imaging of CSF as well as flow in arterial and venous blood vessels. Comparison was performed to trilinear interpolation, divergence-free radial basis functions, divergence-free wavelets, 4DFlowNet, and our network without divergence constraints.

Results: The proposed network div-mDCSRN-Flow outperformed other methods in reconstructing high-resolution velocity fields from synthetic 4D flow MRI in healthy and AD cases. The div-mDCSRN-Flow network reduced error by 22.5% relative to linear interpolation for in vitro core voxels and by 49.5% in edge voxels.

Conclusion: The results demonstrate generalizability of our 4D flow MRI super-resolution and denoising approach due to network training using flow patches and physics-based constraints. The mDCSRN-Flow network can facilitate MRI studies involving CSF flow measurements in cerebral ventricles and association of MRI-based flow metrics with cerebrovascular health.

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
Annals of Biomedical Engineering
Annals of Biomedical Engineering 工程技术-工程:生物医学
CiteScore
7.50
自引率
15.80%
发文量
212
审稿时长
3 months
期刊介绍: Annals of Biomedical Engineering is an official journal of the Biomedical Engineering Society, publishing original articles in the major fields of bioengineering and biomedical engineering. The Annals is an interdisciplinary and international journal with the aim to highlight integrated approaches to the solutions of biological and biomedical problems.
×
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:481959085
Book学术官方微信