Real-time Guidance by Deep Learning of Experienced Operators to Improve the Standardization of Echocardiographic Acquisitions

Overview

Journal Eur Heart J Imaging Methods Pract

Specialty Cardiology & Vascular Diseases

Date 2024 Jul 24

PMID 39045079

Authors

Sigbjorn Sabo

David Pasdeloup

Hakon Neergaard Pettersen

Erik Smistad

Andreas Ostvik

Sindre Hellum Olaisen

Stian Bergseng Stolen

Bjornar Leangen Grenne

Espen Holte

Lasse Lovstakken

Havard Dalen

Affiliations

Soon will be listed here.

Abstract

Aims: Impaired standardization of echocardiograms may increase inter-operator variability. This study aimed to determine whether the real-time guidance of experienced sonographers by deep learning (DL) could improve the standardization of apical recordings.

Methods And Results: Patients ( = 88) in sinus rhythm referred for echocardiography were included. All participants underwent three examinations, whereof two were performed by sonographers and the third by cardiologists. In the first study period (Period 1), the sonographers were instructed to provide echocardiograms for the analyses of the left ventricular function. Subsequently, after brief training, the DL guidance was used in Period 2 by the sonographer performing the second examination. View standardization was quantified retrospectively by a human expert as the primary endpoint and the DL algorithm as the secondary endpoint. All recordings were scored in rotation and tilt both separately and combined and were categorized as standardized or non-standardized. Sonographers using DL guidance had more standardized acquisitions for the combination of rotation and tilt than sonographers without guidance in both periods (all ≤ 0.05) when evaluated by the human expert and DL [except for the apical two-chamber (A2C) view by DL evaluation]. When rotation and tilt were analysed individually, A2C and apical long-axis rotation and A2C tilt were significantly improved, and the others were numerically improved when evaluated by the echocardiography expert. Furthermore, all, except for A2C rotation, were significantly improved when evaluated by DL ( < 0.01).

Conclusion: Real-time guidance by DL improved the standardization of echocardiographic acquisitions by experienced sonographers. Future studies should evaluate the impact with respect to variability of measurements and when used by less-experienced operators.

Clinicaltrialsgov Identifier: NCT04580095.

References

Unlu S, Duchenne J, Mirea O, Pagourelias E, Bezy S, Cvijic M . Impact of apical foreshortening on deformation measurements: a report from the EACVI-ASE Strain Standardization Task Force. Eur Heart J Cardiovasc Imaging. 2019; 21(3):337-343. DOI: 10.1093/ehjci/jez189. View

Morbach C, Gelbrich G, Breunig M, Tiffe T, Wagner M, Heuschmann P . Impact of acquisition and interpretation on total inter-observer variability in echocardiography: results from the quality assurance program of the STAAB cohort study. Int J Cardiovasc Imaging. 2018; 34(7):1057-1065. DOI: 10.1007/s10554-018-1315-3. View

Baron T, Berglund L, Hedin E, Flachskampf F . Test-retest reliability of new and conventional echocardiographic parameters of left ventricular systolic function. Clin Res Cardiol. 2018; 108(4):355-365. PMC: 6426804. DOI: 10.1007/s00392-018-1363-7. View

Narang A, Bae R, Hong H, Thomas Y, Surette S, Cadieu C . Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use. JAMA Cardiol. 2021; 6(6):624-632. PMC: 8204203. DOI: 10.1001/jamacardio.2021.0185. View

Varudo R, Gonzalez F, Leote J, Martins C, Bacariza J, Fernandes A . Machine learning for the real-time assessment of left ventricular ejection fraction in critically ill patients: a bedside evaluation by novices and experts in echocardiography. Crit Care. 2022; 26(1):386. PMC: 9749290. DOI: 10.1186/s13054-022-04269-6. View

Asch F, Mor-Avi V, Rubenson D, Goldstein S, Saric M, Mikati I . Deep Learning-Based Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction: A Point-of-Care Solution. Circ Cardiovasc Imaging. 2021; 14(6):e012293. DOI: 10.1161/CIRCIMAGING.120.012293. View

Otterstad J, Froeland G, St John Sutton M, Holme I . Accuracy and reproducibility of biplane two-dimensional echocardiographic measurements of left ventricular dimensions and function. Eur Heart J. 1997; 18(3):507-13. DOI: 10.1093/oxfordjournals.eurheartj.a015273. View

Mjolstad O, Andersen G, Dalen H, Graven T, Skjetne K, Kleinau J . Feasibility and reliability of point-of-care pocket-size echocardiography performed by medical residents. Eur Heart J Cardiovasc Imaging. 2013; 14(12):1195-202. PMC: 3820150. DOI: 10.1093/ehjci/jet062. View

Thorstensen A, Dalen H, Amundsen B, Aase S, Stoylen A . Reproducibility in echocardiographic assessment of the left ventricular global and regional function, the HUNT study. Eur J Echocardiogr. 2009; 11(2):149-56. DOI: 10.1093/ejechocard/jep188. View

10.

Madani A, Arnaout R, Mofrad M, Arnaout R . Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit Med. 2019; 1. PMC: 6395045. DOI: 10.1038/s41746-017-0013-1. View

11.

Zhang J, Gajjala S, Agrawal P, Tison G, Hallock L, Beussink-Nelson L . Fully Automated Echocardiogram Interpretation in Clinical Practice. Circulation. 2018; 138(16):1623-1635. PMC: 6200386. DOI: 10.1161/CIRCULATIONAHA.118.034338. View

12.

Salte I, Ostvik A, Olaisen S, Karlsen S, Dahlslett T, Smistad E . Deep Learning for Improved Precision and Reproducibility of Left Ventricular Strain in Echocardiography: A Test-Retest Study. J Am Soc Echocardiogr. 2023; 36(7):788-799. DOI: 10.1016/j.echo.2023.02.017. View

13.

Lang R, Badano L, Mor-Avi V, Afilalo J, Armstrong A, Ernande L . Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr. 2015; 28(1):1-39.e14. DOI: 10.1016/j.echo.2014.10.003. View

14.

Ostvik A, Smistad E, Aase S, Haugen B, Lovstakken L . Real-Time Standard View Classification in Transthoracic Echocardiography Using Convolutional Neural Networks. Ultrasound Med Biol. 2018; 45(2):374-384. DOI: 10.1016/j.ultrasmedbio.2018.07.024. View

15.

Schneider M, Bartko P, Geller W, Dannenberg V, Konig A, Binder C . A machine learning algorithm supports ultrasound-naïve novices in the acquisition of diagnostic echocardiography loops and provides accurate estimation of LVEF. Int J Cardiovasc Imaging. 2020; 37(2):577-586. PMC: 7541096. DOI: 10.1007/s10554-020-02046-6. View

16.

Eriksen-Volnes T, Grue J, Olaisen S, Letnes J, Nes B, Lovstakken L . Normalized Echocardiographic Values From Guideline-Directed Dedicated Views for Cardiac Dimensions and Left Ventricular Function. JACC Cardiovasc Imaging. 2023; 16(12):1501-1515. DOI: 10.1016/j.jcmg.2022.12.020. View

17.

Letnes J, Eriksen-Volnes T, Nes B, Wisloff U, Salvesen O, Dalen H . Variability of echocardiographic measures of left ventricular diastolic function. The HUNT study. Echocardiography. 2021; 38(6):901-908. DOI: 10.1111/echo.15073. View

18.

Galderisi M, Cosyns B, Edvardsen T, Cardim N, Delgado V, Di Salvo G . Standardization of adult transthoracic echocardiography reporting in agreement with recent chamber quantification, diastolic function, and heart valve disease recommendations: an expert consensus document of the European Association of.... Eur Heart J Cardiovasc Imaging. 2017; 18(12):1301-1310. DOI: 10.1093/ehjci/jex244. View

19.

Medvedofsky D, Kebed K, Laffin L, Stone J, Addetia K, Lang R . Reproducibility and experience dependence of echocardiographic indices of left ventricular function: Side-by-side comparison of global longitudinal strain and ejection fraction. Echocardiography. 2017; 34(3):365-370. DOI: 10.1111/echo.13446. View

20.

Pasdeloup D, Olaisen S, Ostvik A, Sabo S, Pettersen H, Holte E . Real-Time Echocardiography Guidance for Optimized Apical Standard Views. Ultrasound Med Biol. 2022; 49(1):333-346. DOI: 10.1016/j.ultrasmedbio.2022.09.006. View