• 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

人工智能在心脏磁共振左心室分析临床应用中的进展

Progress in the Clinical Application of Artificial Intelligence for Left Ventricle Analysis in Cardiac Magnetic Resonance.

作者信息

Le Yinghui, Zhao Chongshang, An Jing, Zhou Jiali, Deng Dongdong, He Yi

机构信息

Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 100050 Beijing, China.

Key Laboratory for Biomedical Engineering of Ministry of Education, Institute of Biomedical Engineering, Zhejiang University, 310058 Hangzhou, Zhejiang, China.

出版信息

Rev Cardiovasc Med. 2024 Dec 19;25(12):447. doi: 10.31083/j.rcm2512447. eCollection 2024 Dec.

DOI:10.31083/j.rcm2512447
PMID:39742214
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11683706/
Abstract

Cardiac magnetic resonance (CMR) imaging enables a one-stop assessment of heart structure and function. Artificial intelligence (AI) can simplify and automate work flows and improve image post-processing speed and diagnostic accuracy; thus, it greatly affects many aspects of CMR. This review highlights the application of AI for left heart analysis in CMR, including quality control, image segmentation, and global and regional functional assessment. Most recent research has focused on segmentation of the left ventricular myocardium and blood pool. Although many algorithms have shown a level comparable to that of human experts, some problems, such as poor performance of basal and apical segmentation and false identification of myocardial structure, remain. Segmentation of myocardial fibrosis is another research hotspot, and most patient cohorts of such studies have hypertrophic cardiomyopathy. Whether the above methods are applicable to other patient groups requires further study. The use of automated CMR interpretation for the diagnosis and prognosis assessment of cardiovascular diseases demonstrates great clinical potential. However, prospective large-scale clinical trials are needed to investigate the real-word application of AI technology in clinical practice.

摘要

心脏磁共振成像(CMR)能够一站式评估心脏结构和功能。人工智能(AI)可以简化工作流程并实现自动化,提高图像后处理速度和诊断准确性;因此,它对CMR的许多方面都有很大影响。本综述重点介绍了AI在CMR左心分析中的应用,包括质量控制、图像分割以及整体和局部功能评估。最近的研究主要集中在左心室心肌和血池的分割上。尽管许多算法已显示出与人类专家相当的水平,但仍存在一些问题,如基底部和心尖部分割性能不佳以及心肌结构误识别等。心肌纤维化的分割是另一个研究热点,此类研究的大多数患者队列患有肥厚性心肌病。上述方法是否适用于其他患者群体有待进一步研究。使用自动CMR解释进行心血管疾病的诊断和预后评估显示出巨大的临床潜力。然而,需要进行前瞻性大规模临床试验来研究AI技术在临床实践中的实际应用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9491/11683706/f9624f4d901a/2153-8174-25-12-447-g2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9491/11683706/91fb8e39d528/2153-8174-25-12-447-g1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9491/11683706/f9624f4d901a/2153-8174-25-12-447-g2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9491/11683706/91fb8e39d528/2153-8174-25-12-447-g1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9491/11683706/f9624f4d901a/2153-8174-25-12-447-g2.jpg

相似文献

1
Progress in the Clinical Application of Artificial Intelligence for Left Ventricle Analysis in Cardiac Magnetic Resonance.人工智能在心脏磁共振左心室分析临床应用中的进展
Rev Cardiovasc Med. 2024 Dec 19;25(12):447. doi: 10.31083/j.rcm2512447. eCollection 2024 Dec.
2
Improving the efficiency and accuracy of cardiovascular magnetic resonance with artificial intelligence-review of evidence and proposition of a roadmap to clinical translation.利用人工智能提高心血管磁共振成像的效率和准确性——证据综述及临床转化路线图建议
J Cardiovasc Magn Reson. 2024;26(2):101051. doi: 10.1016/j.jocmr.2024.101051. Epub 2024 Jun 22.
3
An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases.一种用于自动分析大规模非结构化临床心脏磁共振电影数据库的人工智能工具。
Eur Heart J Digit Health. 2023 Jul 13;4(5):370-383. doi: 10.1093/ehjdh/ztad044. eCollection 2023 Oct.
4
Performance of artificial intelligence for biventricular cardiovascular magnetic resonance volumetric analysis in the clinical setting.人工智能在临床双心室心血管磁共振容积分析中的性能。
Int J Cardiovasc Imaging. 2022 Nov;38(11):2413-2424. doi: 10.1007/s10554-022-02649-1. Epub 2022 Jun 29.
5
Implementation and prospective clinical validation of AI-based planning and shimming techniques in cardiac MRI.基于人工智能的心脏 MRI 计划和匀场技术的实施及前瞻性临床验证。
Med Phys. 2022 Jan;49(1):129-143. doi: 10.1002/mp.15327. Epub 2021 Nov 23.
6
Machine Learning-Based Segmentation of Left Ventricular Myocardial Fibrosis from Magnetic Resonance Imaging.基于机器学习的磁共振成像左心室心肌纤维化分割。
Curr Cardiol Rep. 2020 Jun 19;22(8):65. doi: 10.1007/s11886-020-01321-1.
7
Quality of reporting in AI cardiac MRI segmentation studies - A systematic review and recommendations for future studies.人工智能心脏磁共振成像分割研究中的报告质量——一项系统综述及对未来研究的建议。
Front Cardiovasc Med. 2022 Jul 15;9:956811. doi: 10.3389/fcvm.2022.956811. eCollection 2022.
8
Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance.四腔心电影心脏磁共振人工智能分割的研发与验证。
Eur Radiol Exp. 2024 Jul 12;8(1):77. doi: 10.1186/s41747-024-00477-7.
9
Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment.伴有磁化率伪影的心血管磁共振图像:用于心室容积和质量评估的空间注意力人工智能。
J Cardiovasc Magn Reson. 2022 Nov 28;24(1):62. doi: 10.1186/s12968-022-00899-5.
10
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks.基于全卷积网络的自动化心血管磁共振图像分析。
J Cardiovasc Magn Reson. 2018 Sep 14;20(1):65. doi: 10.1186/s12968-018-0471-x.

引用本文的文献

1
Artificial Intelligence Performance in Cardiac Magnetic Resonance Strain Analysis for Aortic Stenosis: Validation with Echocardiography and Healthy Controls.人工智能在主动脉瓣狭窄心脏磁共振应变分析中的性能:与超声心动图及健康对照的验证
Medicina (Kaunas). 2025 May 22;61(6):950. doi: 10.3390/medicina61060950.

本文引用的文献

1
Automated cardiovascular MR myocardial scar quantification with unsupervised domain adaptation.基于无监督域自适应的自动心血管磁共振心肌瘢痕量化。
Eur Radiol Exp. 2024 Aug 14;8(1):93. doi: 10.1186/s41747-024-00497-3.
2
Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging.人工智能赋能心脏磁共振成像在心血管疾病筛查和诊断中的应用。
Nat Med. 2024 May;30(5):1471-1480. doi: 10.1038/s41591-024-02971-2. Epub 2024 May 13.
3
Assessing Regurgitation Severity, Adverse Remodeling, and Fibrosis with CMR in Aortic Regurgitation.
使用心脏磁共振评估主动脉瓣反流中的反流严重程度、不良重构和纤维化。
Curr Cardiol Rep. 2024 May;26(5):413-421. doi: 10.1007/s11886-024-02044-3. Epub 2024 Mar 22.
4
An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases.一种用于自动分析大规模非结构化临床心脏磁共振电影数据库的人工智能工具。
Eur Heart J Digit Health. 2023 Jul 13;4(5):370-383. doi: 10.1093/ehjdh/ztad044. eCollection 2023 Oct.
5
Deep Learning Synthetic Strain: Quantitative Assessment of Regional Myocardial Wall Motion at MRI.深度学习合成应变:MRI对局部心肌壁运动的定量评估
Radiol Cardiothorac Imaging. 2023 May 11;5(3):e220202. doi: 10.1148/ryct.220202. eCollection 2023 Jun.
6
Diffusion models in medical imaging: A comprehensive survey.扩散模型在医学成像中的应用:全面综述。
Med Image Anal. 2023 Aug;88:102846. doi: 10.1016/j.media.2023.102846. Epub 2023 May 23.
7
A bidirectional registration neural network for cardiac motion tracking using cine MRI images.使用电影磁共振成像图像的心脏运动跟踪的双向配准神经网络。
Comput Biol Med. 2023 Jun;160:107001. doi: 10.1016/j.compbiomed.2023.107001. Epub 2023 May 9.
8
Left ventricle segmentation combining deep learning and deformable models with anatomical constraints.结合深度学习和可变形模型与解剖约束的左心室分割。
J Biomed Inform. 2023 Jun;142:104366. doi: 10.1016/j.jbi.2023.104366. Epub 2023 Apr 21.
9
SequenceMorph: A Unified Unsupervised Learning Framework for Motion Tracking on Cardiac Image Sequences.序列形态学:一种用于心脏图像序列运动跟踪的统一无监督学习框架。
IEEE Trans Pattern Anal Mach Intell. 2023 Aug;45(8):10409-10426. doi: 10.1109/TPAMI.2023.3243040. Epub 2023 Jun 30.
10
An Overview of Deep Learning Methods for Left Ventricle Segmentation.深度学习方法在左心室分割中的应用综述。
Comput Intell Neurosci. 2023 Jan 30;2023:4208231. doi: 10.1155/2023/4208231. eCollection 2023.