• 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

基于反向双反转恢复和单次深度学习重建的自由呼吸小儿心脏黑血成像

Free-breathing pediatric cardiac dark-blood imaging with reverse double inversion-recovery and single-shot deep learning reconstruction.

作者信息

Emu Yixin, Shen Quanli, Yao Qiong, Cai Guanke, Chen Zhuo, Hu Junpu, Hu Chenxi, Hu Xihong

机构信息

National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.

Department of Radiology, Children's Hospital of Fudan University, Shanghai, China.

出版信息

Quant Imaging Med Surg. 2025 May 1;15(5):4720-4733. doi: 10.21037/qims-24-1933. Epub 2025 Apr 28.

DOI:10.21037/qims-24-1933
PMID:40384682
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12082608/
Abstract

BACKGROUND

Dark-blood T2-weighted fast spin-echo (DB-FSE) is sensitive to motion, leading to signal dropout artifacts and ghosting artifacts in free-breathing pediatric cardiac imaging, which severely impairs its diagnostic quality. Here, we aimed to fulfill high-resolution motion-robust edema assessment during free-breathing by combining reverse double inversion recovery (RDIR) and single-shot DB-FSE based on artificial intelligence (AI)-assisted compressed sensing (ACS) reconstruction.

METHODS

This prospective study included 20 healthy children and 47 pediatric patients. Three imaging techniques were compared: routine multi-shot DB-FSE based on double inversion recovery (MS-DIR), multi-shot DB-FSE based on RDIR (MS-RDIR), and single-shot DB-FSE based on RDIR (SS-RDIR) with ACS reconstruction. These methods were compared via quantitative metrics, including total acquisition time, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), and qualitative metrics, including myocardial visibility, ghosting artifacts, and overall quality.

RESULTS

In healthy children, the total acquisition time (seconds) of SS-RDIR (64.8±21.8) was significantly less than those of MS-DIR (222.5±69.3, P<0.001) and MS-RDIR (234.0±64.1, P<0.001). The SNR and CNR were comparable (P=0.094 for SNR and P=0.054 for CNR). Ghosting artifacts were significantly reduced in SS-RDIR (4.70±0.18) compared to MS-DIR (3.95±0.28, P<0.001) and MS-RDIR (3.97±0.31, P<0.001), whereas overall quality was improved in SS-RDIR (4.42±0.19) compared to MS-DIR (3.87±0.27, P=0.004) and MS-RDIR (3.95±0.34, P=0.010). In patients, SS-RDIR significantly reduced the total acquisition time compared to MS-DIR (62.1±24.0 216.6±74.2, P<0.001) and MS-RDIR (229.8±79.2, P<0.001), with comparable SNR (P=0.065) and CNR (P=0.089). SS-RDIR also showed less severe ghosting artifacts (4.94±0.11) compared to MS-DIR (3.77±0.29, P<0.001) and MS-RDIR (3.78±0.34, P<0.001), and better quality (3.96±0.52) than MS-DIR (3.61±0.40, P=0.023).

CONCLUSIONS

SS-RDIR with ACS reconstruction offers substantially shorter scan time and superior image quality than traditional multi-shot techniques. This approach enhances clinical workflow and patient comfort, facilitating a broader application of DB-FSE in pediatric cardiac imaging.

摘要

背景

黑血T2加权快速自旋回波(DB-FSE)对运动敏感,在小儿心脏自由呼吸成像中会导致信号丢失伪影和鬼影伪影,严重影响其诊断质量。在此,我们旨在通过基于人工智能(AI)辅助压缩感知(ACS)重建的反向双反转恢复(RDIR)和单次激发DB-FSE相结合,在自由呼吸过程中实现高分辨率的运动稳健性水肿评估。

方法

这项前瞻性研究纳入了20名健康儿童和47名儿科患者。比较了三种成像技术:基于双反转恢复的常规多次激发DB-FSE(MS-DIR)、基于RDIR的多次激发DB-FSE(MS-RDIR)以及基于RDIR并采用ACS重建的单次激发DB-FSE(SS-RDIR)。通过定量指标(包括总采集时间、信噪比(SNR)和对比噪声比(CNR))以及定性指标(包括心肌可见性、鬼影伪影和整体质量)对这些方法进行比较。

结果

在健康儿童中,SS-RDIR的总采集时间(秒)(64.8±21.8)显著短于MS-DIR(222.5±69.3,P<0.001)和MS-RDIR(234.0±64.1,P<0.001)。SNR和CNR具有可比性(SNR的P=0.094,CNR的P=0.054)。与MS-DIR(3.95±0.28,P<0.001)和MS-RDIR(3.97±0.31,P<0.001)相比,SS-RDIR中的鬼影伪影显著减少(4.70±0.18),而与MS-DIR(3.87±0.27,P=0.004)和MS-RDIR(3.95±0.34,P=0.010)相比,SS-RDIR的整体质量得到改善(4.42±0.19)。在患者中,与MS-DIR(62.1±24.0对216.6±74.2,P<0.001)和MS-RDIR(229.8±79.2,P<0.001)相比,SS-RDIR显著缩短了总采集时间,SNR(P=0.065)和CNR(P=0.089)具有可比性。与MS-DIR(3.77±0.29,P<0.001)和MS-RDIR(3.78±0.34,P<0.001)相比,SS-RDIR的鬼影伪影也较轻(4.94±0.11),且质量(3.96±0.52)优于MS-DIR(3.61±0.40,P=0.023)。

结论

采用ACS重建的SS-RDIR比传统的多次激发技术提供了显著更短的扫描时间和更高的图像质量。这种方法增强了临床工作流程和患者舒适度,有助于DB-FSE在小儿心脏成像中的更广泛应用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/0646144b726f/qims-15-05-4720-f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/ef67caa01a65/qims-15-05-4720-f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/b3c237ec98ce/qims-15-05-4720-f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/1a49f74fcda2/qims-15-05-4720-f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/38c9ec407a9b/qims-15-05-4720-f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/cd2564440da1/qims-15-05-4720-f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/0646144b726f/qims-15-05-4720-f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/ef67caa01a65/qims-15-05-4720-f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/b3c237ec98ce/qims-15-05-4720-f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/1a49f74fcda2/qims-15-05-4720-f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/38c9ec407a9b/qims-15-05-4720-f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/cd2564440da1/qims-15-05-4720-f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2e48/12082608/0646144b726f/qims-15-05-4720-f6.jpg

相似文献

1
Free-breathing pediatric cardiac dark-blood imaging with reverse double inversion-recovery and single-shot deep learning reconstruction.基于反向双反转恢复和单次深度学习重建的自由呼吸小儿心脏黑血成像
Quant Imaging Med Surg. 2025 May 1;15(5):4720-4733. doi: 10.21037/qims-24-1933. Epub 2025 Apr 28.
2
Reverse double inversion-recovery: Improving motion robustness of cardiac T -weighted dark-blood turbo spin-echo sequence.反转双反转恢复:提高心脏 T2 加权黑血涡轮自旋回波序列的运动鲁棒性。
J Magn Reson Imaging. 2018 Jun;47(6):1498-1508. doi: 10.1002/jmri.25886. Epub 2017 Nov 7.
3
Dark blood T2-weighted imaging of the human heart with AI-assisted compressed sensing: a patient cohort study.人工智能辅助压缩感知下的人体心脏黑血T2加权成像:一项患者队列研究
Quant Imaging Med Surg. 2023 Mar 1;13(3):1699-1710. doi: 10.21037/qims-22-607. Epub 2023 Feb 9.
4
Application of deep learning techniques for breath-hold, high-precision T2-weighted magnetic resonance imaging of the abdomen.深度学习技术在腹部屏气、高精度T2加权磁共振成像中的应用。
Abdom Radiol (NY). 2025 May;50(5):2312-2320. doi: 10.1007/s00261-024-04675-0. Epub 2024 Nov 13.
5
AI-assisted compressed sensing and parallel imaging sequences for MRI of patients with nasopharyngeal carcinoma: comparison of their capabilities in terms of examination time and image quality.人工智能辅助压缩感知和并行成像序列在鼻咽癌患者 MRI 中的应用:检查时间和图像质量方面的性能比较。
Eur Radiol. 2023 Nov;33(11):7686-7696. doi: 10.1007/s00330-023-09742-6. Epub 2023 May 23.
6
On the loss of image contrast in double-inversion-recovery prepared T2* MRI of Intramyocardial hemorrhage.心肌内出血的双反转恢复准备 T2*MRI 中图像对比的损失。
Magn Reson Imaging. 2024 Jan;105:125-132. doi: 10.1016/j.mri.2023.11.010. Epub 2023 Nov 21.
7
A multi-band double-inversion radial fast spin-echo technique for T2 cardiovascular magnetic resonance mapping of the heart.一种用于心脏 T2 心血管磁共振成像的多带宽双反转径向快速自旋回波技术。
J Cardiovasc Magn Reson. 2018 Jul 19;20(1):49. doi: 10.1186/s12968-018-0470-y.
8
Clinical comparison of single-shot EPI, readout-segmented EPI and TGSE-BLADE for diffusion-weighted imaging of cerebellopontine angle tumors on 3 tesla.3.0T 磁共振单次激发 EPI、分段读出 EPI 及 TGSE-BLADE 序列在桥小脑角肿瘤扩散加权成像中的临床对比研究。
Magn Reson Imaging. 2021 Dec;84:76-83. doi: 10.1016/j.mri.2021.09.009. Epub 2021 Sep 21.
9
Application of single shot free-breathing fast imaging employing steady state sequence in cardiac magnetic resonance imaging.单次屏气自由呼吸快速成像稳态序列在心脏磁共振成像中的应用
Clin Physiol Funct Imaging. 2015 Mar;35(2):159-66. doi: 10.1111/cpf.12140. Epub 2014 Mar 3.
10
Effect of Deep Learning Reconstruction on Respiratory-triggered T2-weighted MR Imaging of the Liver: A Comparison between the Single-shot Fast Spin-echo and Fast Spin-echo Sequences.深度学习重建对肝脏呼吸触发 T2 加权 MR 成像的影响:单次激发快速自旋回波与快速自旋回波序列的比较。
Magn Reson Med Sci. 2024 Apr 1;23(2):214-224. doi: 10.2463/mrms.mp.2022-0111. Epub 2023 Mar 29.

本文引用的文献

1
Emerging technologies in pediatric radiology: current developments and future prospects.儿科放射学中的新兴技术:当前的发展和未来的前景。
Pediatr Radiol. 2024 Aug;54(9):1428-1436. doi: 10.1007/s00247-024-05997-3. Epub 2024 Jul 16.
2
Body MRI in pediatrics: where we are and what the future holds.儿科身体磁共振成像:我们目前的状况与未来发展
Pediatr Radiol. 2025 Jan;55(1):8-11. doi: 10.1007/s00247-024-05984-8. Epub 2024 Jul 9.
3
DFUSNN: zero-shot dual-domain fusion unsupervised neural network for parallel MRI reconstruction.DFUSNN:用于并行磁共振成像重建的零-shot 双域融合无监督神经网络。
Phys Med Biol. 2024 May 10;69(10). doi: 10.1088/1361-6560/ad3dbc.
4
Adaptive Knowledge Distillation for High-Quality Unsupervised MRI Reconstruction With Model-Driven Priors.基于模型驱动先验的自适应知识蒸馏实现高质量无监督 MRI 重建。
IEEE J Biomed Health Inform. 2024 Jun;28(6):3571-3582. doi: 10.1109/JBHI.2024.3365784. Epub 2024 Jun 6.
5
An applicability study of rapid artificial intelligence-assisted compressed sensing (ACS) in anal fistula magnetic resonance imaging.快速人工智能辅助压缩感知(ACS)在肛瘘磁共振成像中的适用性研究
Heliyon. 2023 Dec 6;10(1):e22817. doi: 10.1016/j.heliyon.2023.e22817. eCollection 2024 Jan 15.
6
Application research of AI-assisted compressed sensing technology in MRI scanning of the knee joint: 3D-MRI perspective.人工智能辅助压缩感知技术在膝关节 MRI 扫描中的应用研究:3D-MRI 视角。
Eur Radiol. 2024 May;34(5):3046-3058. doi: 10.1007/s00330-023-10368-x. Epub 2023 Nov 7.
7
Deep Learning Super-Resolution Reconstruction for Fast and Motion-Robust T2-weighted Prostate MRI.深度学习超分辨率重建用于快速和运动稳健的前列腺 T2 加权 MRI。
Radiology. 2023 Sep;308(3):e230427. doi: 10.1148/radiol.230427.
8
High-Resolution 3D MRI With Deep Generative Networks via Novel Slice-Profile Transformation Super-Resolution.通过新型切片轮廓变换超分辨率技术利用深度生成网络实现高分辨率3D磁共振成像
IEEE Access. 2023;11:95022-95036. doi: 10.1109/access.2023.3307577. Epub 2023 Aug 22.
9
Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction.基于混合深度学习和迭代重建的快速、低剂量医学成像生成。
Cell Rep Med. 2023 Jul 18;4(7):101119. doi: 10.1016/j.xcrm.2023.101119.
10
Feasibility of AI-assisted compressed sensing protocols in knee MR imaging: a prospective multi-reader study.人工智能辅助压缩感知协议在膝关节磁共振成像中的可行性:一项前瞻性多读者研究。
Eur Radiol. 2023 Dec;33(12):8585-8596. doi: 10.1007/s00330-023-09823-6. Epub 2023 Jun 29.