Myocardial strain is a dimensionless parameter reflecting the degree of deformation of the whole or local myocardium under stress, which can quantitatively detect myocardial injury and guide the early diagnosis, intervention and prognostic assessment of cardiac diseases. Cardiac ultrasound, cardiac CT and cardiac magnetic resonance can all be used for strain imaging and analysis, with two-dimensional speckle-tracking echocardiography being the most widely used means of myocardial strain detection today. However, due to inter-observer variations in manual analysis of myocardial strain and differences in the imaging systems and analysis software, the consistency and reproducibility of measured strain values among vendors are poor, limiting the clinical application of myocardial strain. Artificial intelligence (AI) can overcome the defects of strain measurement to a certain extent through automatic strain calculation and image quality assessment, which has a broad developmental prospect. This review focuses on the progress of AI-assisted measurement of myocardial strain in ultrasound, magnetic resonance, and other imaging modalities, as well as its application to disease diagnosis and patient prognosis assessment. This will improve the efficiency and consistency of strain measurement and promote the routine application of myocardial strain to clinical practice, which will play an incremental role in assessing myocardial injury and cardiac function. However, most of the current studies involve small sample sizes and lack external validation, and the reliability of their results needs to be further verified.
LI Xinxin, BIAN Yize, ZHAO Hang, JIANG Meng. Research progress in the artificial intelligence-assisted measurement of myocardial strain. Journal of Shanghai Jiao Tong University (Medical Science)[J], 2024, 44(6): 773-778 doi:10.3969/j.issn.1674-8115.2024.06.013
LI Xinxin and BIAN Yize were responsible for topic selection, literature collection, paper writing and revision; ZHAO Hang and JIANG Meng determined the topic selection and guided the paper revision. All the authors have read the last version of paper and consented for submission.
利益冲突声明
所有作者声明不存在利益冲突。
COMPETING INTERESTS
All authors disclose no relevant conflict of interests.
PURWOWIYOTO S L, HALOMOAN R. Highlighting the role of global longitudinal strain assessment in valvular heart disease[J]. Egypt Heart J, 2022, 74(1): 46.
THAVENDIRANATHAN P, POULIN F, LIM K D, et al. Use of myocardial strain imaging by echocardiography for the early detection of cardiotoxicity in patients during and after cancer chemotherapy: a systematic review[J]. J Am Coll Cardiol, 2014, 63(25 Pt A): 2751-2768.
FARSALINOS K E, DARABAN A M, ÜNLÜ S, et al. Head-to-head comparison of global longitudinal strain measurements among nine different vendors: the EACVI/ASE inter-vendor comparison study[J]. J Am Soc Echocardiogr, 2015, 28(10): 1171-1181, e2.
NEGISHI K, LUCAS S, NEGISHI T, et al. What is the primary source of discordance in strain measurement between vendors: imaging or analysis?[J]. Ultrasound Med Biol, 2013, 39(4): 714-720.
GHADIMI S, AUGER D A, FENG X, et al. Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrapping[J]. J Cardiovasc Magn Reson, 2021, 23(1): 20.
SALTE I M, ØSTVIK A, SMISTAD E, et al. Artificial intelligence for automatic measurement of left ventricular strain in echocardiography[J]. JACC Cardiovasc Imaging, 2021, 14(10): 1918-1928.
SENGUPTA P P, NARULA J. Cardiac strain as a universal biomarker: interpreting the sounds of uneasy heart muscle cells[J]. JACC Cardiovasc Imaging, 2014, 7(5): 534-536.
ERNANDE L, THIBAULT H, BERGEROT C, et al. Systolic myocardial dysfunction in patients with type 2 diabetes mellitus: identification at MR imaging with cine displacement encoding with stimulated echoes[J]. Radiology, 2012, 265(2): 402-409.
NIU J Q, ZENG M, WANG Y, et al. Sensitive marker for evaluation of hypertensive heart disease: extracellular volume and myocardial strain[J]. BMC Cardiovasc Disord, 2020, 20(1): 292.
AARSAETHER E, RÖSNER A, STRAUMBOTN E, et al. Peak longitudinal strain most accurately reflects myocardial segmental viability following acute myocardial infarction: an experimental study in open-chest pigs[J]. Cardiovasc Ultrasound, 2012, 10: 23.
MANGION K, MCCOMB C, AUGER D A, et al. Magnetic resonance imaging of myocardial strain after acute ST-segment-elevation myocardial infarction: a systematic review[J]. Circ Cardiovasc Imaging, 2017, 10(8): e006498.
HELM R H, BYRNE M, HELM P A, et al. Three-dimensional mapping of optimal left ventricular pacing site for cardiac resynchronization[J]. Circulation, 2007, 115(8): 953-961.
LIM P, BUAKHAMSRI A, POPOVIC Z B, et al. Longitudinal strain delay index by speckle tracking imaging: a new marker of response to cardiac resynchronization therapy[J]. Circulation, 2008, 118(11): 1130-1137.
DENG L. Artificial intelligence in the rising wave of deep learning: the historical path and future outlook[perspectives][J]. IEEE Signal Process Mag, 2018, 35(1): 180,173-177.
HSIAO H C W, CHEN S H F, TSAI J J P. Deep learning for risk analysis of specific cardiovascular diseases using environmental data and outpatient records[C/OL]//2016 IEEE 16th International Conference on Bioinformatics and Bioengineering (BIBE), Taichung, Taiwan, China. IEEE, 2016: 369-372[2023-12-19].https://ieeexplore.ieee.org/document/7790013.
UPTON R, MUMITH A, BEQIRI A, et al. Automated echocardiographic detection of severe coronary artery disease using artificial intelligence[J]. JACC Cardiovasc Imaging, 2022, 15(5): 715-727.
COTELLA J I, SLIVNICK J A, SANDERSON E, et al. Artificial intelligence based left ventricular ejection fraction and global longitudinal strain in cardiac amyloidosis[J]. Echocardiography, 2023, 40(3): 188-195.
HEIMDAL A, STØYLEN A, TORP H, et al. Real-time strain rate imaging of the left ventricle by ultrasound[J]. J Am Soc Echocardiogr, 1998, 11(11): 1013-1019.
PIRAT B, KHOURY D S, HARTLEY C J, et al. A novel feature-tracking echocardiographic method for the quantitation of regional myocardial function: validation in an animal model of ischemia-reperfusion[J]. J Am Coll Cardiol, 2008, 51(6): 651-659.
MOR-AVI V, LANG R M, BADANO L P, et al. Current and evolving echocardiographic techniques for the quantitative evaluation of cardiac mechanics: ASE/EAE consensus statement on methodology and indications endorsed by the Japanese Society of Echocardiography[J]. Eur J Echocardiogr, 2011, 12(3): 167-205.
PÉREZ DE ISLA L, BALCONES D V, FERNÁNDEZ-GOLFÍN C, et al. Three-dimensional-wall motion tracking: a new and faster tool for myocardial strain assessment: comparison with two-dimensional-wall motion tracking[J]. J Am Soc Echocardiogr, 2009, 22(4): 325-330.
KAWAKAMI H, WRIGHT L, NOLAN M, et al. Feasibility, reproducibility, and clinical implications of the novel fully automated assessment for global longitudinal strain[J]. J Am Soc Echocardiogr, 2021, 34(2): 136-145.e2.
EVAIN E, SUN Y Y, FARAZ K, et al. Motion estimation by deep learning in 2D echocardiography: synthetic dataset and validation[J]. IEEE Trans Med Imaging, 2022, 41(8): 1911-1924.
LIU S, BOSE, AHMED A, et al. Artificial intelligence-based assessment of indices of right ventricular function[J]. J Cardiothorac Vasc Anesth, 2020, 34(10): 2698-2702.
HUANG K C, HUANG C S, SU M Y, et al. Artificial intelligence aids cardiac image quality assessment for improving precision in strain measurements[J]. JACC Cardiovasc Imaging, 2021, 14(2): 335-345.
ZERHOUNI E A, PARISH D M, ROGERS W J, et al. Human heart: tagging with MR imaging‒ a method for noninvasive assessment of myocardial motion[J]. Radiology, 1988, 169(1): 59-63.
CLAUS P, OMAR A M S, PEDRIZZETTI G, et al. Tissue tracking technology for assessing cardiac mechanics: principles, normal values, and clinical applications[J]. JACC Cardiovasc Imaging, 2015, 8(12): 1444-1460.
GRÖSCHEL J, KUHNT J, VIEZZER D, et al. Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking: a cardiovascular MR study in health and disease[J]. Eur Radiol, 2024, 34(2): 1003-1015.
CHENG N N, BONAZZOLA R, RAVIKUMAR N, et al. A generative framework for predicting myocardial strain from cine-cardiac magnetic resonance imaging[C]//Annual Conference on Medical Image Understanding and Analysis. Cham: Springer, 2022: 482-493.
MISKINYTE E, BUCIUS P, ERLEY J, et al. Assessment of global longitudinal and circumferential strain using computed tomography feature tracking: intra-individual comparison with CMR feature tracking and myocardial tagging in patients with severe aortic stenosis[J]. J Clin Med, 2019, 8(9): 1423.
WONG K C, TEE M, CHEN M, et al. Regional infarction identification from cardiac CT images: a computer-aided biomechanical approach[J]. Int J Comput Assist Radiol Surg, 2016, 11(9): 1573-1583.
KOEHLER S, KUHM J, HUFFAKER T, et al. Artificial intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach[J]. Res Sq, 2024.DOI: 10.21203/rs.3.rs-3785677/v1.
KARAGODIN I, CARVALHO SINGULANE C, WOODWARD G M, et al. Echocardiographic correlates of in-hospital death in patients with acute COVID-19 infection: the world alliance societies of echocardiography (WASE-COVID) study[J]. J Am Soc Echocardiogr, 2021, 34(8): 819-830.
O'DRISCOLL J M, HAWKES W, BEQIRI A, et al. Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography[J]. Eur Heart J Open, 2022, 2(5): oeac059.
AKERMAN A, BERNARD L, DESCHAMPS T, et al. Automated contouring of non-contrast echocardiograms result in similar estimates of left ventricular function to manually contoured contrast-enhanced images in chemotherapy patients[J]. Eur Heart J Cardiovasc Imaging, 2022, 23(Suppl 1): jeab289.013.
NARULA S, SHAMEER K, SALEM OMAR A M, et al. Machine-learning algorithms to automate morphological and functional assessments in 2D echocardiography[J]. J Am Coll Cardiol, 2016, 68(21): 2287-2295.
KUI B R, XUE P, JIANG Y, et al. World Health Organization guidance Ethical and Governance of Artificial Intelligence for Health and implications for China[J]. National Medical Journal of China, 2022, 102(12): 833-837.
