人工智能在超声心动图中的临床应用

刘硕 ,  马春燕

中国医科大学学报 ›› 2026, Vol. 55 ›› Issue (6) : 481 -486.

PDF (389KB)
中国医科大学学报 ›› 2026, Vol. 55 ›› Issue (6) : 481 -486. DOI: 10.12007/j.issn.0258‐4646.2026.06.001
专家述评

人工智能在超声心动图中的临床应用

作者信息 +

Clinical application of artificial intelligence in echocardiography

Author information +
文章历史 +
PDF (397K)

摘要

随着人工智能 (AI) 技术的快速发展,其在医学领域的应用深度和广度不断拓展,对临床工作产生了深远影响。超声心动图作为诊断心血管疾病的首选影像学方法,具有快速、准确、实时、无创等优势,但传统人工分析模式存在操作繁琐、耗时较长、观察者间一致性差等局限性。AI技术与超声心动图的深度融合,有望突破这些瓶颈,推动超声诊断向自动化、智能化方向迈进。本文系统总结了AI在超声心动图领域的临床应用现状,包括心腔自动分割和容积定量、心肌应变分析、心脏瓣膜病的自动分析、辅助诊断和预后预测模型、超声图像获取的智能指导等多个研究方向,详细阐述了相关技术原理、临床应用效果以及准确性验证结果,还探讨了目前AI在超声心动图中的应用局限性和未来发展方向,从而为进一步的研究和临床推广提供参考。

Abstract

With the rapid development of artificial intelligence (AI) technology,its application in the field of medicine has expanded in both depth and breadth,resulting in significant changes in clinical practice. As the preferred imaging modality for the diagnosis of cardiovascular diseases,echocardiography provides the advantages of rapidity,accuracy,real-time imaging,and noninvasiveness. However,the traditional manual analysis paradigm is limited by cumbersome operation,notable time consumption,and poor interobserver agreement. The deep integration of AI technology and echocardiography is expected to overcome these bottlenecks and advance echocardiographic diagnosis toward automation and intelligence. This review systematically addresses the current status of the clinical application of AI in the field of echocardiography,covering multiple research directions,including automatic chamber segmentation and volume quantification,myocardial strain analysis,automatic analysis of valvular heart disease,auxiliary diagnosis and prognosis prediction models,and image acquisition guidance. We elaborate on the relevant technical principles,clinical application efficacy,and validation results for accuracy. In addition,this review discusses the existing limitations and future directions for the development of AI applications in echocardiography,offering a reference for both research and clinical implementation.

关键词

人工智能 / 超声心动图 / 心血管疾病 / 自动定量分析 / 辅助诊断

Key words

artificial intelligence / echocardiography / cardiovascular disease / automatic quantitative analysis / auxiliary diagnosis

引用本文

引用格式 ▾
刘硕,马春燕. 人工智能在超声心动图中的临床应用[J]. 中国医科大学学报, 2026, 55(6): 481-486 DOI:10.12007/j.issn.0258‐4646.2026.06.001

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

LANG RM,BADANO LP,MOR—AVI V,et al. Recommendations for cardiac chamber quantification by echocardiography in adults:an up date from the American Society of Echocardiography and the European Association of Cardiovascular Imaging [J]. Eur Heart J Cardiovasc Imaging,2015,16 (3):233-270. DOI:10.1093/ehjci/jev014.

[2]

QAYYUM SN. A comprehensive review of applications of artificial in telligence in echocardiography [J]. Curr Probl Cardiol,2024,49 (2):102250. DOI:10.1016/j.cpcardiol.2023.102250.

[3]

SVERIC KM,ULBRICH S,DINDANE Z,et al. Improved assessment of left ventricular ejection fraction using artificial intelligence in echocardiography:a comparative analysis with cardiac magnetic reso- nance imaging [J]. Int J Cardiol,2024,394:131383. DOI:10.1016/j.ijcard.2023.131383.

[4]

VRUDHULA A,VUKADINOVIC M,HAEFFELE C,et al. Automated deep learning phenotyping of tricuspid regurgitation in echocardiogra phy [J]. JAMA Cardiol,2025,10 (6):595-602. DOI:10.1001/jama-cardio.2025.0498.

[5]

TOKODI M,SHAH R,JAMTHIKAR A,et al. Deep learning model of diastolic dysfunction risk stratifies the progression of early-stage aortic stenosis [J]. JACC Cardiovasc Imaging,2025,18 (2):150-165. DOI:10.1016/j.jcmg.2024.07.017.

[6]

VALSARAJ A,KALMADY SV,SHARMA V,et al. Development and validation of echocardiography-based machine-learning models to predict mortality [J]. EBioMedicine,2023,90:104479. DOI:10.1016/j.ebiom.2023.104479.

[7]

OIKONOMOU EK,SANGHA V,SHANKAR SV,et al. Artificial intelligence-enabled electrocardiography and echocardiography to track preclinical progression of transthyretin amyloid cardiomyopathy [J]. Eur Heart J,2025,46 (37):3651-3662. DOI:10.1093/eurheartj/ehaf450.

[8]

ØSTVIK A,SMISTAD E,AASE SA,et al. Real-time standard view classification in transthoracic echocardiography using convolutional neural networks [J]. Ultrasound Med Biol,2019,45 (2):374-384. DOI:10.1016/j.ultrasmedbio.2018.07.024.

[9]

BOMBELLI M,VANOLI J,FACCHETTI R,et al. Impact of the in crease in left ventricular mass on the risk of long-term cardiovascular mortality:a prospective cohort study [J]. Hypertension,2023,80 (6):1321-1330. DOI:10.1161/HYPERTENSIONAHA.122.19988.

[10]

CHEN L,ZHANG C,WANG J,et al. Left atrial strain measured by 4D Auto LAQ echocardiography is significantly correlated with high risk of thromboembolism in patients with non-valvular atrial fibrilla tion [J]. Quant Imaging Med Surg,2021,11 (9):3920-3931. DOI:10.21037/qims-20-1381.

[11]

SAHASHI Y,IEKI H,YUAN V,et al. Artificial intelligence auto mation of echocardiographic measurements [J]. J Am Coll Cardiol, 2025,86 (13):964-978. DOI:10.1016/j.jacc.2025.07.053.

[12]

ZHU Y,BAO YW,ZHENG KC,et al. Quantitative assessment of right ventricular size and function with multiple parameters from artificial intelligence-based three-dimensional echocardiography:a comparative study with cardiac magnetic resonance [J]. Echocardio-graphy,2022,39 (2):223-232. DOI:10.1111/echo.15292.

[13]

ZHANG Y,WANG YB,YAO GH,et al. Right ventricular volume and function by three-dimensional echocardiography:results of the echocardiographic measurements in normal Chinese adults (EM INCA)Ⅱ [J]. MedComm (2020),2024,5 (5):e550. DOI:10.1002/mco2.550.

[14]

CHOI YJ,LEE HJ,PARK JS,et al. Left ventricular global longitu dinal strain as a prognosticator in hypertrophic cardiomyopathy with a low-normal left ventricular ejection fraction [J]. Eur Heart J Car diovasc Imaging,2023,24 (10):1374-1383. DOI:.

[15]

KWAN AC,CHANG EW,JAIN I,et al. Deep learning-derived myo cardial strain [J]. JACC Cardiovasc Imaging,2024,17 (7):715-725. DOI:10.1016/j.jcmg.2024.01.011.

[16]

UEYAMA H,KUNO T,TAKAGI H,et al. Prognostic value of left ventricular global longitudinal strain in mitral regurgitation:a sys tematic review [J]. Heart Fail Rev,2023,28 (2):465-483. DOI:10.1007/s10741-022-10265-3.

[17]

TADIC M,SALA C,CARUGO S,et al. Left ventricular global lon gitudinal strain in secondary hypertension:a meta-analysis of echo cardiographic studies [J]. Eur J Intern Med,2022,96:81-89. DOI:10.1016/j.ejim.2021.10.018.

[18]

HU X,BAO Y,ZHU Y,et al. Predicting left ventricular myocardial fibrosis in patients with hypertrophic cardiomyopathy by speckle tracking automated functional imaging [J]. Ultrasound Med Biol, 2023,49 (5):1309-1317. DOI:10.1016/j.ultrasmedbio.2023.01.020.

[19]

KAWAKAMI H,WRIGHT L,NOLAN M,et al. Feasibility,repro ducibility,and clinical implications of the novel fully automated as sessment for global longitudinal strain [J]. J Am Soc Echocardiogr, 2021,34 (2):136-145.e2. DOI:10.1016/j.echo.2020.09.011.

[20]

CARLUCCIO E,CAMELI M,ROSSI A,et al. Left atrial strain in the assessment of diastolic function in heart failure:a machine learning approach [J]. Circ Cardiovasc Imaging,2023,16 (2):e014605. DOI:10.1161/CIRCIMAGING.122.014605.

[21]

LI Y,SUN C,ZHANG L,et al. Feasibility,reproducibility,and prognostic value of fully automated measurement of right ventricular longitudinal strain [J]. J Am Soc Echocardiogr,2022,35 (6):609-619. DOI:10.1016/j.echo.2022.01.016.

[22]

PRAZ F,BORGER MA,LANZ J,et al. 2025 ESC/EACTS Guide lines for the management of valvular heart disease [J]. Eur Heart J, 2025,46 (44):4635-4736. DOI:10.1093/eurheartj/ehaf194.

[23]

ZHANG D,YU M,LIN X,et al. Artificial intelligence diagnosis and heatmap agent for mitral valve prolapse using 3D cine echo cardiography [J]. iScience,2025,28 (8):113033. DOI:10.1016/j.isci.2025.113033.

[24]

FIORETTI G,TOLOMEI A,CIARAMELLA P,et al. Study of degenerative mitral regurgitation using three-dimensional echocar diography and EchoPAC GE health care software 4D auto MVQ: comparison between transthoracic and transesophageal examination [J]. Echocardiography,2024,41 (12):e70040. DOI:10.1111/echo.70040.

[25]

PARK J,KIM J,JEON J,et al. Artificial intelligence-enhanced comprehensive assessment of the aortic valve stenosis continuum in echocardiography [J]. EBioMedicine,2025,112:105560. DOI:10.1016/j.ebiom.2025.105560.

[26]

GARCÍA-MARTÍN A,LÁZARO-RIVERA C,FERNÁNDEZ-GOLFÍN C,et al. Accuracy and reproducibility of novel echocardio graphic three-dimensional automated software for the assessment of the aortic root in candidates for thanscatheter aortic valve replace ment [J]. Eur Heart J Cardiovasc Imaging,2016,17 (7):772-778. DOI:10.1093/ehjci/jev204.

[27]

KHAMOOSHIAN A,AMADOR Y,HAI T,et al. Dynamic three-dimensional geometry of the aortic valve apparatus-a feasibility study [J]. J Cardiothorac Vasc Anesth,2017,31 (4):1290-1300. DOI:10.1053/j.jvca.2017.03.004.

[28]

GUEZ D,BOROUMAND G,RUGGIERO NJ,et al. Automated and manual measurements of the aortic annulus with ECG-gated cardiac CT angiography prior to transcatheter aortic valve replacement: comparison with 3D-transesophageal echocardiography [J]. Acad Radiol,2017,24 (5):587-593. DOI:10.1016/j.acra.2016.12.008.

[29]

CALLEJA A,THAVENDIRANATHAN P,IONASEC RI,et al. Automated quantitative 3-dimensional modeling of the aortic valve and root by 3-dimensional transesophageal echocardiography in normals,aortic regurgitation,and aortic stenosis:comparison to computed tomography in normals and clinical implications [J]. Circ Cardiovasc Imaging,2013,6 (1):99-108. DOI:10.1161/CIRCIMAGING.112.976993.

[30]

LONG A,HAGGERTY CM,FINER J,et al. Deep learning for echo analysis,tracking,and evaluation of mitral regurgitation (DELINEATE-MR) [J]. Circulation,2024,150 (12):911-922. DOI:10.1161/CIRCULATIONAHA.124.068996.

[31]

SANTARPINO G,TAVERNA G,CALABRESE V,et al. Exploring imaging depth:a pilot study about 2D vs. 4D echocardiography for tricuspid valve evaluation [J]. Rev Cardiovasc Med,2025,26 (5):41556. DOI:10.31083/RCM41556.

[32]

OIKONOMOU EK,VAID A,HOLSTE G,et al. Artificial intel ligence-guided detection of under-recognised cardiomyopathies on point-of-care cardiac ultrasonography:a multicentre study [J]. Lancet Digit Health,2025,7 (2):e113-e123. DOI:10.1016/S2589-7500(24)00249-8.

[33]

LAI C,YIN M,KHOLMOVSKI EG,et al. Multimodal AI to forecast arrhythmic death in hypertrophic cardiomyopathy [J]. Nat Cardiovasc Res,2025,4 (7):891-903. DOI:10.1038/s44161-025-00679-1.

[34]

CIKES M,SANCHEZ-MARTINEZ S,CLAGGETT B,et al. Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy [J]. Eur J Heart Fail,2019,21 (1):74-85. DOI:10.1002/ejhf.1333.

[35]

NARANG A,BAE R,HONG H,et al. Utility of a deep-learning algorithm to guide novices to acquire echocardiograms for limited diagnostic use [J]. JAMA Cardiol,2021,6 (6):624-632. DOI:10.1001/jamacardio.2021.0185.

[36]

MOR-AVI V,KHANDHERIA B,KLEMPFNER R,et al. Real-time artificial intelligence-based guidance of echocardiographic imaging by novices:image quality and suitability for diagnostic interpretation and quantitative analysis [J]. Circ Cardiovasc Imaging,2023,16 (11):e015569. DOI:10.1161/CIRCIMAGING.123.015569.

基金资助

国家自然科学基金(82472007)

AI Summary AI Mindmap
PDF (389KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉