{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T03:58:43Z","timestamp":1777521523662,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005366","name":"University of Oslo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005366","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Speckle tracking echocardiography (STE) provides quantification of left ventricular (LV) deformation and is useful in the assessment of LV function. STE is increasingly being used clinically, and every effort to simplify and standardize STE is important. Manual outlining of regions of interest (ROIs) is labor intensive and may influence assessment of strain values.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>We hypothesized that a deep learning (DL) model, trained on clinical echocardiographic exams, can be combined with a readily available echocardiographic analysis software, to automate strain calculation with comparable fidelity to trained cardiologists.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>Data consisted of still frame echocardiographic images with cardiologist-defined ROIs from 672 clinical echocardiographic exams from a university hospital outpatient clinic. Exams included patients with ischemic heart disease, heart failure, valvular disease, and conduction abnormalities, and some healthy subjects. An EfficientNetB1-based architecture was employed, and different techniques and properties including data set size, data quality, augmentations, and transfer learning were evaluated. DL predicted ROIs were reintroduced into commercially available echocardiographic analysis software to automatically calculate strain values.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>DL-automated strain calculations had an average absolute difference of 0.75 (95% CI 0.58\u20130.92) for global longitudinal strain (GLS), and 1.16 (95% CI 1.03\u20131.29) for single-projection longitudinal strain (LS), compared to operators. A Bland\u2013Altman plot revealed no obvious bias, though there were fewer outliers in the lower average LS ranges. Techniques and data properties yielded no significant increase\/decrease in performance.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The study demonstrates that DL-assisted, automated strain measurements are feasible, and provide results within interobserver variation. Employing DL in echocardiographic analyses could further facilitate adoption of STE parameters in clinical practice and research, and improve reproducibility.\n<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12880-024-01470-7","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:29:48Z","timestamp":1731371388000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A deep learning based method for left ventricular strain measurements: repeatability and accuracy compared to experienced echocardiographers"],"prefix":"10.1186","volume":"24","author":[{"given":"Magnus","family":"Rogstadkjernet","sequence":"first","affiliation":[]},{"given":"Sigurd Z.","family":"Zha","sequence":"additional","affiliation":[]},{"given":"Lars G.","family":"Kl\u00e6boe","sequence":"additional","affiliation":[]},{"given":"Camilla K.","family":"Larsen","sequence":"additional","affiliation":[]},{"given":"John M.","family":"Aalen","sequence":"additional","affiliation":[]},{"given":"Esther","family":"Scheirlynck","sequence":"additional","affiliation":[]},{"given":"Bj\u00f8rn-Jostein","family":"Singstad","sequence":"additional","affiliation":[]},{"given":"Steven","family":"Droogmans","sequence":"additional","affiliation":[]},{"given":"Bernard","family":"Cosyns","sequence":"additional","affiliation":[]},{"given":"Otto A.","family":"Smiseth","sequence":"additional","affiliation":[]},{"given":"Kristina H.","family":"Haugaa","sequence":"additional","affiliation":[]},{"given":"Thor","family":"Edvardsen","sequence":"additional","affiliation":[]},{"given":"Eigil","family":"Samset","sequence":"additional","affiliation":[]},{"given":"P\u00e5l H.","family":"Brekke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"issue":"2","key":"1470_CR1","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1161\/CIRCIMAGING.109.910521","volume":"3","author":"Eek Christian","year":"2010","unstructured":"Christian Eek, Bj\u00f8rnar Grenne, Harald Brunvand, Svend Aakhus, Knut Endresen, Hol Per K, et al. Strain echocardiography and wall motion score index predicts final infarct size in patients with non\u2013ST-Segment\u2013elevation myocardial infarction. Circulation. Cardiovasc Imaging. 2010;3(2):187\u201394.","journal-title":"Cardiovasc Imaging"},{"issue":"15","key":"1470_CR2","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1093\/eurheartj\/ehv529","volume":"37","author":"OA Smiseth","year":"2016","unstructured":"Smiseth OA, Torp H, Opdahl A, Haugaa KH, Urheim S. Myocardial strain imaging: how useful is it in clinical decision making? Eur Heart J. 2016;37(15):1196\u2013207.","journal-title":"Eur Heart J"},{"issue":"21","key":"1470_CR3","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1136\/heartjnl-2014-305538","volume":"100","author":"K Kalam","year":"2014","unstructured":"Kalam K, Otahal P, Marwick TH. Prognostic implications of global LV dysfunction: a systematic review and meta-analysis of global longitudinal strain and ejection fraction. Heart. 2014;100(21):1673\u201380.","journal-title":"Heart"},{"issue":"10","key":"1470_CR4","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1093\/ehjci\/jes115","volume":"13","author":"LG Kearney","year":"2012","unstructured":"Kearney LG, Lu K, Ord M, Patel SK, Profitis K, Matalanis G, et al. Global longitudinal strain is a strong independent predictor of all-cause mortality in patients with aortic stenosis. Eur Heart J Cardiovasc Imaging. 2012;13(10):827\u201333.","journal-title":"Eur Heart J Cardiovasc Imaging"},{"issue":"8","key":"1470_CR5","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.echo.2017.04.009","volume":"30","author":"LG Kl\u00e6boe","year":"2017","unstructured":"Kl\u00e6boe LG, H\u00e5land TSF, Leren IS, ter Bekke RMA, Brekke PH, R\u00f8sj\u00f8 H, et al. Prognostic value of left ventricular deformation parameters in patients with severe aortic stenosis: a pilot study of the usefulness of strain echocardiography. J Am Soc Echocardiogr. 2017;30(8):727\u2013735.e1.","journal-title":"J Am Soc Echocardiogr"},{"issue":"9","key":"1470_CR6","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1001\/jamacardio.2018.2288","volume":"3","author":"EM Vollema","year":"2018","unstructured":"Vollema EM, Sugimoto T, Shen M, Tastet L, Ng ACT, Abou R, et al. Association of left ventricular global longitudinal strain with asymptomatic severe aortic stenosis. JAMA Cardiol. 2018;3(9):839\u201347.","journal-title":"JAMA Cardiol"},{"issue":"3","key":"1470_CR7","first-page":"223","volume":"4","author":"NT Olsen","year":"2011","unstructured":"Olsen NT, Sogaard P, Larsson HBW, Goetze JP, Jons C, Mogelvang R, et al. Speckle-tracking echocardiography for predicting outcome in chronic aortic regurgitation during conservative management and after surgery. JACC: Cardiovasc Imaging. 2011;4(3):223\u201330.","journal-title":"JACC: Cardiovasc Imaging"},{"issue":"12","key":"1470_CR8","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1016\/j.echo.2008.09.023","volume":"21","author":"P Lancellotti","year":"2008","unstructured":"Lancellotti P, Cosyns B, Zacharakis D, Attena E, Van Camp G, Gach O, et al. Importance of left ventricular longitudinal function and functional reserve in patients with degenerative mitral regurgitation: assessment by two-dimensional speckle tracking. J Am Soc Echocardiogr. 2008;21(12):1331\u20136.","journal-title":"J Am Soc Echocardiogr"},{"issue":"9","key":"1470_CR9","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","volume":"24","author":"J De Fauw","year":"2018","unstructured":"De Fauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med. 2018;24(9):1342\u201350.","journal-title":"Nat Med"},{"issue":"7639","key":"1470_CR10","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115\u20138.","journal-title":"Nature"},{"issue":"11","key":"1470_CR11","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","volume":"25","author":"MP McBee","year":"2018","unstructured":"McBee MP, Awan OA, Colucci AT, Ghobadi CW, Kadom N, Kansagra AP, et al. Deep learning in radiology. Acad Radiol. 2018;25(11):1472\u201380.","journal-title":"Acad Radiol"},{"key":"1470_CR12","unstructured":"Salte IM, \u00d8stvik A, Smistad E, Melichova D, Nguyen TM, Karlsen S, et al. Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography. JACC: Cardiovascular Imaging. 2021. Available from: https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1936878X21003636. Cited 2021 Sep 15."},{"issue":"16","key":"1470_CR13","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","volume":"138","author":"J Zhang","year":"2018","unstructured":"Zhang J, Gajjala SM, Agrawal P, Tison GHM, Hallock LAB, Beussink-Nelson LR, et al. Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation. 2018;138(16):1623\u201335.","journal-title":"Circulation"},{"issue":"6","key":"1470_CR14","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1007\/s00246-022-03015-7","volume":"45","author":"L Li","year":"2022","unstructured":"Li L, Homer P, Craft M, Kutty S, Putschoegl A, Marshall A, et al. Machine learning-enabled fully automated assessment of left ventricular volume, ejection fraction and strain: experience in pediatric and young adult echocardiography. Pediatr Cardiol. 2022;45(6):1183\u201391.","journal-title":"Pediatr Cardiol"},{"issue":"2","key":"1470_CR15","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.echo.2020.09.011","volume":"34","author":"H Kawakami","year":"2021","unstructured":"Kawakami H, Wright L, Nolan M, Potter EL, Yang H, Marwick TH. Feasibility, reproducibility, and clinical implications of the novel fully automated assessment for global longitudinal strain. J Am Soc Echocardiogr. 2021;34(2):136\u2013145.e2.","journal-title":"J Am Soc Echocardiogr"},{"key":"1470_CR16","unstructured":"Lohr S. What Ever Happened to IBM\u2019s Watson? The New York Times. 2021; Available from: https:\/\/www.nytimes.com\/2021\/07\/16\/technology\/what-happened-ibm-watson.html. Cited 2022 Nov 6."},{"key":"1470_CR17","unstructured":"MIT Technology Review. Google\u2019s medical AI was super accurate in a lab. Real life was a different story. Available from: https:\/\/www.technologyreview.com\/2020\/04\/27\/1000658\/google-medical-ai-accurate-lab-real-life-clinic-covid-diabetes-retina-disease\/. Cited 2022 Nov 6."},{"issue":"7623","key":"1470_CR18","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/538020a","volume":"538","author":"D Castelvecchi","year":"2016","unstructured":"Castelvecchi D. Can we open the black box of AI? Nat News. 2016;538(7623):20.","journal-title":"Nat News"},{"issue":"1","key":"1470_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/ehjci\/jeu184","volume":"16","author":"JU Voigt","year":"2015","unstructured":"Voigt JU, Pedrizzetti G, Lysyansky P, Marwick TH, Houle H, Baumann R, et al. Definitions for a common standard for 2D speckle tracking echocardiography: consensus document of the EACVI\/ASE\/Industry Task Force to standardize deformation imaging. Eur Heart J Cardiovasc Imaging. 2015;16(1):1\u201311.","journal-title":"Eur Heart J Cardiovasc Imaging"},{"issue":"9","key":"1470_CR20","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","volume":"38","author":"S Leclerc","year":"2019","unstructured":"Leclerc S, Smistad E, Pedrosa J, \u00d8stvik A, Cervenansky F, Espinosa F, et al. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging. 2019;38(9):2198\u2013210.","journal-title":"IEEE Trans Med Imaging"},{"issue":"10","key":"1470_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345\u201359.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"1470_CR22","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115(3):211\u201352.","journal-title":"Int J Comput Vis"},{"issue":"3","key":"1470_CR23","first-page":"249","volume":"31","author":"SB Kotsiantis","year":"2007","unstructured":"Kotsiantis SB. Supervised machine learning: a review of classification techniques. Informatica. 2007;31(3):249\u201369.","journal-title":"Informatica"},{"key":"1470_CR24","doi-asserted-by":"publisher","unstructured":"Refaeilzadeh P, Tang L, Liu H. Cross-Validation. In: LIU L, \u00d6ZSU MT, editors. Encyclopedia of database systems. Boston, MA: Springer US; 2009. p. 532\u20138. https:\/\/doi.org\/10.1007\/978-0-387-39940-9_565. Cited 2022 Nov 6.","DOI":"10.1007\/978-0-387-39940-9_565"},{"key":"1470_CR25","unstructured":"Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:190511946. 2020; Available from: http:\/\/arxiv.org\/abs\/1905.11946. Cited 2022 Jan 17."},{"key":"#cr-split#-1470_CR26.1","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:150504597 [cs]. 2015 May 18","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"#cr-split#-1470_CR26.2","unstructured":"Available from: http:\/\/arxiv.org\/abs\/1505.04597. Cited 2020 Mar 22."},{"key":"1470_CR27","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. arXiv:151203385. 2015; Available from: http:\/\/arxiv.org\/abs\/1512.03385. Cited 2022 Jan 19."},{"issue":"8","key":"1470_CR28","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1093\/ehjci\/jex140","volume":"18","author":"T Sugimoto","year":"2017","unstructured":"Sugimoto T, Dulgheru R, Bernard A, Ilardi F, Contu L, Addetia K, et al. Echocardiographic reference ranges for normal left ventricular 2D strain: results from the EACVI NORRE study. Eur Heart J Cardiovasc Imaging. 2017;18(8):833\u201340.","journal-title":"Eur Heart J Cardiovasc Imaging"},{"key":"1470_CR29","doi-asserted-by":"crossref","unstructured":"Ferdian E, Suinesiaputra A, Fung K, Aung N, Lukaschuk E, Barutcu A, et al. Fully automated myocardial strain estimation from cardiovascular MRI\u2013tagged images using a deep learning framework in the UK Biobank. Radiol Cardiothorac Imaging. 2020;2(1). Available from: https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC7051160\/. Cited 2021 Jan 9.","DOI":"10.1148\/ryct.2020190032"},{"key":"1470_CR30","doi-asserted-by":"publisher","first-page":"102078","DOI":"10.1016\/j.artmed.2021.102078","volume":"116","author":"D Karimi","year":"2021","unstructured":"Karimi D, Warfield SK, Gholipour A. Transfer learning in medical image segmentation: new insights from analysis of the dynamics of model parameters and learned representations. Artif Intell Med. 2021;116:102078.","journal-title":"Artif Intell Med"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-024-01470-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-024-01470-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-024-01470-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T01:02:20Z","timestamp":1731373340000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-024-01470-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1470"],"URL":"https:\/\/doi.org\/10.1186\/s12880-024-01470-7","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"17 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All data were from studies approved by Regional Committees for Medical Research Ethics South East Norway (REK). For patients with myocardial infarction, informed consent was waived by REK. Informed consent was obtained from all other subjects. All methods were carried out in accordance with relevant guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"305"}}