Artificial intelligence fully automated myocardial strain quantification for risk stratification following acute myocardial infarction

Sören J Backhaus, Haneen Aldehayat, Johannes T Kowallick, Ruben Evertz, Torben Lange, Shelby Kutty, Boris Bigalke, Matthias Gutberlet, Gerd Hasenfuß, Holger Thiele, Thomas Stiermaier, Ingo Eitel, Andreas Schuster, Sören J Backhaus, Haneen Aldehayat, Johannes T Kowallick, Ruben Evertz, Torben Lange, Shelby Kutty, Boris Bigalke, Matthias Gutberlet, Gerd Hasenfuß, Holger Thiele, Thomas Stiermaier, Ingo Eitel, Andreas Schuster

Abstract

Feasibility of automated volume-derived cardiac functional evaluation has successfully been demonstrated using cardiovascular magnetic resonance (CMR) imaging. Notwithstanding, strain assessment has proven incremental value for cardiovascular risk stratification. Since introduction of deformation imaging to clinical practice has been complicated by time-consuming post-processing, we sought to investigate automation respectively. CMR data (n = 1095 patients) from two prospectively recruited acute myocardial infarction (AMI) populations with ST-elevation (STEMI) (AIDA STEMI n = 759) and non-STEMI (TATORT-NSTEMI n = 336) were analysed fully automated and manually on conventional cine sequences. LV function assessment included global longitudinal, circumferential, and radial strains (GLS/GCS/GRS). Agreements were assessed between automated and manual strain assessments. The former were assessed for major adverse cardiac event (MACE) prediction within 12 months following AMI. Manually and automated derived GLS showed the best and excellent agreement with an intraclass correlation coefficient (ICC) of 0.81. Agreement was good for GCS and poor for GRS. Amongst automated analyses, GLS (HR 1.12, 95% CI 1.08-1.16, p < 0.001) and GCS (HR 1.07, 95% CI 1.05-1.10, p < 0.001) best predicted MACE with similar diagnostic accuracy compared to manual analyses; area under the curve (AUC) for GLS (auto 0.691 vs. manual 0.693, p = 0.801) and GCS (auto 0.668 vs. manual 0.686, p = 0.425). Amongst automated functional analyses, GLS was the only independent predictor of MACE in multivariate analyses (HR 1.10, 95% CI 1.04-1.15, p < 0.001). Considering high agreement of automated GLS and equally high accuracy for risk prediction compared to the reference standard of manual analyses, automation may improve efficiency and aid in clinical routine implementation.Trial registration: ClinicalTrials.gov, NCT00712101 and NCT01612312.

Conflict of interest statement

The authors declare no competing interests.

© 2022. The Author(s).

Figures

Figure 1
Figure 1
Flow chart of study data. AIDA STEMI, Abciximab i.v. versus i.c. in ST-elevation Myocardial Infarction; CMR, cardiac magnetic resonance; FU, follow-up; MACE, major adverse cardiac events; NSTEMI, non-ST-segment–elevation myocardial infarction; STEMI, ST-segment–elevation myocardial infarction; and TATORT NSTEMI, Thrombus Aspiration in Thrombus Containing Culprit Lesions in Non-ST-Elevation Myocardial Infarction.
Figure 2
Figure 2
Cardioavascular magnetic resonance LAX images with automated contouring at end systole (top) and end diastole (bottom); 4CV (left) and 2CV (right). 2CV, 2 chamber view; 4CV, 4 chamber view; LAX, long axis.
Figure 3
Figure 3
SAX image slices with automated contouring starting from the apical view and ending with the outflow tract of the LV. LV, left ventricle; SAX, short axis.
Figure 4
Figure 4
Bland-Altmann plots for agreement of manual and automated strain; GLS, GCS 3 slices and GCS all slices. Agreement between manual and automated strain values represented by Bland-Altmann plot, y axis represents the difference (manual-automated) and x axis is the mean of manual and automated values. GCS, global circumferential strain; GLS, global longitudinal strain.
Figure 5
Figure 5
Kaplan–Meier curves assessing survival for manual and automated GLS and GCS. All values dichotomized by their respective medians, time to event represents time to MACE. GCS, global circumferential strain; GLS, global longitudinal strain; MACE, major adverse cardiac events.

References

    1. Wang OJ, Wang Y, Chen J, Krumholz HM. Recent trends in hospitalization for acute myocardial infarction. Am. J. Cardiol. 2012;109(11):1589–1593. doi: 10.1016/j.amjcard.2012.01.381.
    1. Roger VL, et al. Heart disease and stroke statistics–2011 update: A report from the American Heart Association. Circulation. 2011;123(4):e18–e209. doi: 10.1161/CIR.0b013e3182009701.
    1. Smith SC, Jr, et al. Our time: A call to save preventable death from cardiovascular disease (heart disease and stroke) J. Am. Coll. Cardiol. 2012;60(22):2343–2348. doi: 10.1016/j.jacc.2012.08.962.
    1. Roffi M, et al. 2015 ESC Guidelines for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation: Task Force for the Management of Acute Coronary Syndromes in Patients Presenting without Persistent ST-Segment Elevation of the European Society of Cardiology (ESC) Eur. Heart J. 2016;37(3):267–315. doi: 10.1093/eurheartj/ehv320.
    1. Epstein AE, et al. ACC/AHA/HRS 2008 Guidelines for Device-Based Therapy of Cardiac Rhythm Abnormalities: A report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines (Writing Committee to Revise the ACC/AHA/NASPE 2002 Guideline Update for Implantation of Cardiac Pacemakers and Antiarrhythmia Devices): Developed in collaboration with the American Association for Thoracic Surgery and Society of Thoracic Surgeons. Circulation. 2008;117(21):e350–e408. doi: 10.1161/CIRCUALTIONAHA.108.189742.
    1. Dagres N, Hindricks G. Risk stratification after myocardial infarction: Is left ventricular ejection fraction enough to prevent sudden cardiac death? Eur. Heart J. 2013;34(26):1964–1971. doi: 10.1093/eurheartj/eht109.
    1. Eitel I, Stiermaier T, Lange T, Rommel KP, Koschalka A, Kowallick JT, Lotz J, Kutty S, Gutberlet M, Hasenfuß G, Thiele H, Schuster A. Cardiac magnetic resonance myocardial feature tracking for optimized prediction of cardiovascular events following myocardial infarction. JACC Cardiovasc. Imaging. 2018;11(10):1433–1444. doi: 10.1016/j.jcmg.2017.11.034.
    1. Buss SJ, Krautz B, Hofmann N, Sander Y, Rust L, Giusca S, Galuschky C, Seitz S, Giannitsis E, Pleger S, Raake P, Most P, Katus HA, Korosoglou G. Prediction of functional recovery by cardiac magnetic resonance feature tracking imaging in first time ST-elevation myocardial infarction. Comparison to infarct size and transmurality by late gadolinium enhancement. Int. J. Cardiol. 2015;183:162–170. doi: 10.1016/j.ijcard.2015.01.022.
    1. Bucius P, Erley J, Tanacli R, Zieschang V, Giusca S, Korosoglou G, Steen H, Stehning C, Pieske B, Pieske-Kraigher E, Schuster A, Lapinskas T, Kelle S. Comparison of feature tracking, fast-SENC, and myocardial tagging for global and segmental left ventricular strain. ESC Heart Fail. 2020;7(2):523–532. doi: 10.1002/ehf2.12576.
    1. Schuster A, Hor KN, Kowallick JT, Beerbaum P, Kutty S. Cardiovascular magnetic resonance myocardial feature tracking: Concepts and clinical applications. Circ. Cardiovasc. Imaging. 2016;9(4):e004077. doi: 10.1161/CIRCIMAGING.115.004077.
    1. Schuster A, Lange T, Backhaus SJ, Strohmeyer C, Boom PC, Matz J, Kowallick JT, Lotz J, Steinmetz M, Kutty S, Bigalke B, Gutberlet M, de Waha-Thiele S, Desch S, Hasenfuß G, Thiele H, Stiermaier T, Eitel I. Fully Automated cardiac assessment for diagnostic and prognostic stratification following myocardial infarction. J. Am. Heart Assoc. 2020;9(18):e016612. doi: 10.1161/JAHA.120.016612.
    1. Mangion K, McComb C, Auger DA, Epstein FH, Berry C. Magnetic resonance imaging of myocardial strain after acute ST-segment-elevation myocardial infarction: A systematic review. Circ. Cardiovasc. Imaging. 2017;10(8):e006498. doi: 10.1161/CIRCIMAGING.117.006498.
    1. Eitel I, Wöhrle J, Suenkel H, Meissner J, Kerber S, Lauer B, Pauschinger M, Birkemeyer R, Axthelm C, Zimmermann R, Neuhaus P, Brosteanu O, de Waha S, Desch S, Gutberlet M, Schuler G, Thiele H. Intracoronary compared with intravenous bolus abciximab application during primary percutaneous coronary intervention in ST-segment elevation myocardial infarction: Cardiac magnetic resonance substudy of the AIDA STEMI trial. J. Am. Coll. Cardiol. 2013;61(13):1447–1454. doi: 10.1016/j.jacc.2013.01.048.
    1. de Waha S, Eitel I, Desch S, Scheller B, Böhm M, Lauer B, Gawaz M, Geisler T, Gunkel O, Bruch L, Klein N, Pfeiffer D, Schuler G, Zeymer U, Thiele H. Thrombus aspiration in ThrOmbus containing culpRiT lesions in Non-ST-Elevation Myocardial Infarction (TATORT-NSTEMI): Study protocol for a randomized controlled trial. Trials. 2013;14:110. doi: 10.1186/1745-6215-14-110.
    1. Kramer CM, Barkhausen J, Bucciarelli-Ducci C, Flamm SD, Kim RJ, Nagel E. Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J. Cardiovasc. Magn. Reson. 2020;22(1):17. doi: 10.1186/s12968-020-00607-1.
    1. Backhaus SJ, Metschies G, Billing M, Schmidt-Rimpler J, Kowallick JT, Gertz RJ, Lapinskas T, Pieske-Kraigher E, Pieske B, Lotz J, Bigalke B, Kutty S, Hasenfuß G, Kelle S, Schuster A. Defining the optimal temporal and spatial resolution for cardiovascular magnetic resonance imaging feature tracking. J. Cardiovasc. Magn. Reson. 2021;23(1):60. doi: 10.1186/s12968-021-00740-5.
    1. Kowallick JT, Morton G, Lamata P, Jogiya R, Kutty S, Lotz J, Hasenfuß G, Nagel E, Chiribiri A, Schuster A. Inter-study reproducibility of left ventricular torsion and torsion rate quantification using MR myocardial feature tracking. J. Magn. Reson. Imaging. 2016;43(1):128–137. doi: 10.1002/jmri.24979.
    1. Gertz RJ, Lange T, Kowallick JT, Backhaus SJ, Steinmetz M, Staab W, Kutty S, Hasenfuß G, Lotz J, Schuster A. Inter-vendor reproducibility of left and right ventricular cardiovascular magnetic resonance myocardial feature-tracking. PLoS ONE. 2018;13(3):e0193746. doi: 10.1371/journal.pone.0193746.
    1. Grothues F, Smith GC, Moon JC, Bellenger NG, Collins P, Klein HU, Pennell DJ. Comparison of interstudy reproducibility of cardiovascular magnetic resonance with two-dimensional echocardiography in normal subjects and in patients with heart failure or left ventricular hypertrophy. Am. J. Cardiol. 2002;90(1):29–34. doi: 10.1016/s0002-9149(02)02381-0.
    1. Bland JM, Altman DG. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet (London, England) 1986;1(8476):307–310. doi: 10.1016/S0140-6736(86)90837-8.
    1. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics. 1988;44(3):837–845. doi: 10.2307/2531595.
    1. Harrild DM, Marcus E, Hasan B, Alexander ME, Powell AJ, Geva T, McElhinney DB. Impact of transcatheter pulmonary valve replacement on biventricular strain and synchrony assessed by cardiac magnetic resonance feature tracking. Circ. Cardiovasc. Interv. 2013;6(6):680–687. doi: 10.1161/CIRCINTERVENTIONS.113.000690.
    1. Stiermaier T, Lange T, Chiribiri A, Möller C, Graf T, Villnow C, Raaz U, Villa A, Kowallick JT, Lotz J, Hasenfuß G, Thiele H, Schuster A, Eitel I. Left ventricular myocardial deformation in Takotsubo syndrome: A cardiovascular magnetic resonance myocardial feature tracking study. Eur. Radiol. 2018;28(12):5160–5170. doi: 10.1007/s00330-018-5475-2.
    1. Taylor RJ, Moody WE, Umar F, Edwards NC, Taylor TJ, Stegemann B, Townend JN, Hor KN, Steeds RP, Mazur W, Leyva F. Myocardial strain measurement with feature-tracking cardiovascular magnetic resonance: Normal values. Eur. Heart J. Cardiovasc. Imaging. 2015;16(8):871–881. doi: 10.1093/ehjci/jev006.
    1. Ochs A, Riffel J, Ochs MM, Arenja N, Fritz T, Galuschky C, Schuster A, Bruder O, Mahrholdt H, Giannitsis E, Frey N, Katus HA, Buss SJ, André F. Myocardial mechanics in dilated cardiomyopathy: Prognostic value of left ventricular torsion and strain. J. Cardiovasc. Magn. Reson. 2021;23(1):136. doi: 10.1186/s12968-021-00829-x.
    1. Backhaus SJ, Metschies G, Zieschang V, Erley J, Mahsa Zamani S, Kowallick JT, Lapinskas T, Pieske B, Lotz J, Kutty S, Hasenfuß G, Kelle S, Schuster A. Head-to-head comparison of cardiovascular MR feature tracking cine versus acquisition-based deformation strain imaging using myocardial tagging and strain encoding. Magn. Reson. Med. 2021;85(1):357–368. doi: 10.1002/mrm.28437.
    1. Ruijsink B, Puyol-Antón E, Oksuz I, Sinclair M, Bai W, Schnabel JA, Razavi R, King AP. Fully automated, quality-controlled cardiac analysis from CMR: Validation and large-scale application to characterize cardiac function. JACC Cardiovasc. Imaging. 2020;13(3):684–695. doi: 10.1016/j.jcmg.2019.05.030.
    1. Knackstedt C, Bekkers SC, Schummers G, Schreckenberg M, Muraru D, Badano LP, Franke A, Bavishi C, Omar AM, Sengupta PP. Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: The FAST-EFs multicenter study. J. Am. Coll. Cardiol. 2015;66(13):1456–1466. doi: 10.1016/j.jacc.2015.07.052.
    1. Pedrizzetti G, Claus P, Kilner PJ, Nagel E. Principles of cardiovascular magnetic resonance feature tracking and echocardiographic speckle tracking for informed clinical use. J. Cardiovasc. Magn. Reson. 2016;18(1):51. doi: 10.1186/s12968-016-0269-7.
    1. Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial intelligence in precision cardiovascular medicine. J. Am. Coll. Cardiol. 2017;69(21):2657–2664. doi: 10.1016/j.jacc.2017.03.571.
    1. Betancur J, Commandeur F, Motlagh M, Sharir T, Einstein AJ, Bokhari S, Fish MB, Ruddy TD, Kaufmann P, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Germano G, Otaki Y, Tamarappoo BK, Dey D, Berman DS, Slomka PJ. Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: A multicenter study. JACC Cardiovasc. Imaging. 2018;11(11):1654–1663. doi: 10.1016/j.jcmg.2018.01.020.
    1. Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH, Andreini D, Budoff MJ, Cademartiri F, Callister TQ, Chang HJ, Chinnaiyan K, Chow BJ, Cury RC, Delago A, Gomez M, Gransar H, Hadamitzky M, Hausleiter J, Hindoyan N, Slomka PJ. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis. Eur. Heart J. 2017;38(7):500–507. doi: 10.1093/eurheartj/ehw188.
    1. Scatteia A, Baritussio A, Bucciarelli-Ducci C. Strain imaging using cardiac magnetic resonance. Heart Fail. Rev. 2017;22(4):465–476. doi: 10.1007/s10741-017-9621-8.
    1. Corral Acero J, Schuster A, Zacur E, Lange T, Stiermaier T, Backhaus SJ, Thiele H, Bueno-Orovio A, Lamata P, Eitel I, Grau V. Understanding and improving risk assessment after myocardial infarction using automated left ventricular shape analysis. JACC Cardiovasc. Imaging. 2022 doi: 10.1016/j.jcmg.2021.11.027.
    1. Ersbøll M, Valeur N, Mogensen UM, Andersen MJ, Møller JE, Velazquez EJ, Hassager C, Søgaard P, Køber L. Prediction of all-cause mortality and heart failure admissions from global left ventricular longitudinal strain in patients with acute myocardial infarction and preserved left ventricular ejection fraction. J. Am. Coll. Cardiol. 2013;61(23):2365–2373. doi: 10.1016/j.jacc.2013.02.061.

Source: PubMed

Sponsorit ja yhteistyökumppanit

Sairaudet

Huumeiden interventiot

3
Tilaa