{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:55:28Z","timestamp":1792803328890,"version":"4.5.0"},"reference-count":39,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>The ejection fraction (EF) is a vital metric for assessing cardiovascular function through cardiac ultrasound. Manual evaluation is time-consuming and exhibits high variability among observers. Deep-learning techniques offer precise and autonomous EF predictions, yet these methods often lack explainability. Accurate heart failure prediction using cardiac ultrasound is challenging due to operator dependency and inconsistent video quality, resulting in significant interobserver variability. To address this, we developed a method integrating convolutional neural networks (CNN) and transformer models for direct EF estimation from ultrasound video scans. This article introduces a Residual Transformer Module (RTM) that extends a 3D ResNet-based network to analyze (2D + t) spatiotemporal cardiac ultrasound video scans. The proposed method, EFNet, utilizes cardiac ultrasound video images for end-to-end EF value prediction. Performance evaluation on the EchoNet-Dynamic dataset yielded a mean absolute error (MAE) of 3.7 and an R2 score of 0.82. Experimental results demonstrate that EFNet outperforms state-of-the-art techniques, providing accurate EF predictions.<\/jats:p>","DOI":"10.7717\/peerj-cs.2506","type":"journal-article","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T08:42:36Z","timestamp":1737448956000},"page":"e2506","source":"Crossref","is-referenced-by-count":9,"title":["EFNet: estimation of left ventricular ejection fraction from cardiac ultrasound videos using deep learning"],"prefix":"10.7717","volume":"11","author":[{"given":"Waqas","family":"Ali","sequence":"first","affiliation":[{"name":"Computer Science Department, University of Engineering and Technology, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wesam","family":"Alsabban","sequence":"additional","affiliation":[{"name":"Department of Computer and Network Engineering, College of Computing, Umm Al-Qura University, Makkah, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Shahbaz","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Engineering and Technology, Lahore, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Al-Laith","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Copenhagen, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bassam","family":"Almogadwy","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Science, Taibah University, Medina, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,1,21]]},"reference":[{"issue":"1","key":"10.7717\/peerj-cs.2506\/ref-1","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1038\/s41598-023-27493-8","article-title":"Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study","volume":"13","author":"Adekkanattu","year":"2023","journal-title":"Scientific Reports"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-2","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.hfc.2021.12.002","article-title":"Advances in machine learning approaches to heart failure with preserved ejection fraction","volume":"18","author":"Ahmad","year":"2022","journal-title":"Heart Failure Clinics"},{"key":"10.7717\/peerj-cs.2506\/ref-3","first-page":"348","article-title":"Multi-frame attention network for left ventricle segmentation in 3D echocardiography","author":"Ahn","year":"2021"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-4","doi-asserted-by":"publisher","first-page":"e117","DOI":"10.1016\/S2589-7500(21)00256-9","article-title":"Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study","volume":"4","author":"Bachtiger","year":"2022","journal-title":"The Lancet Digital Health"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-5","doi-asserted-by":"publisher","first-page":"16","DOI":"10.5493\/wjem.v12.i2.16","article-title":"Machine learning algorithm using publicly available echo database for simplified \u201cvisual estimation\u201d of left ventricular ejection fraction","volume":"12","author":"Blaivas","year":"2022","journal-title":"World Journal of Experimental Medicine"},{"key":"10.7717\/peerj-cs.2506\/ref-6","first-page":"1","article-title":"Deep semantic segmentation of echocardiographic images using vision transformers","author":"Bosco","year":"2023"},{"key":"10.7717\/peerj-cs.2506\/ref-7","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1002\/ejhf.1957","article-title":"Role of cardiovascular imaging in cancer patients receiving cardiotoxic therapies: a position statement on behalf of the heart failure association (HFA), the european association of cardiovascular imaging (EACVI) and the cardio-oncology council of the european society of cardiology (ESC)","volume":"22","author":"\u010celutkien\u0117","year":"2020","journal-title":"European Journal of Heart Failure"},{"key":"10.7717\/peerj-cs.2506\/ref-8","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1109\/TMI.2022.3229136","article-title":"Cyclical self-supervision for semi-supervised ejection fraction prediction from echocardiogram videos","volume":"42","author":"Dai","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"9765","key":"10.7717\/peerj-cs.2506\/ref-9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ejmp.2016.12.005","article-title":"Computer aided diagnosis of coronary artery disease, myocardial infarction and carotid atherosclerosis using ultrasound images: a review","volume":"33","author":"Faust","year":"2017","journal-title":"Physica Medica: PM"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-10","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TMI.2020.3035253","article-title":"CA-Net: comprehensive attention convolutional neural networks for explainable medical image segmentation","volume":"40","author":"Gu","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.2506\/ref-11","first-page":"1","article-title":"3DCNN model for left ventricular ejection fraction evaluation in echocardiography","author":"Hassan","year":"2023"},{"key":"10.7717\/peerj-cs.2506\/ref-12","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"9","key":"10.7717\/peerj-cs.2506\/ref-13","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1016\/j.amjcard.2009.01.024","article-title":"Usefulness of a combination of systolic function by left ventricular ejection fraction and diastolic function by e\/e\u2019 to predict prognosis in patients with heart failure","volume":"103","author":"Hirata","year":"2009","journal-title":"The American Journal of Cardiology"},{"issue":"4","key":"10.7717\/peerj-cs.2506\/ref-14","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1007\/s11548-019-01954-w","article-title":"Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training","volume":"38","author":"Jafari","year":"2019","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"12","key":"10.7717\/peerj-cs.2506\/ref-15","doi-asserted-by":"publisher","first-page":"8747","DOI":"10.21037\/qims-23-542","article-title":"Transformers in medical image segmentation: a narrative review","volume":"13","author":"Khan","year":"2023","journal-title":"Quantitative Imaging in Medicine and Surgery"},{"issue":"1","key":"10.7717\/peerj-cs.2506\/ref-16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.echo.2014.10.003","article-title":"Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the american society of echocardiography and the european association of cardiovascular imaging","volume":"28","author":"Lang Roberto","year":"2015","journal-title":"Journal of the American Society of Echocardiography"},{"key":"10.7717\/peerj-cs.2506\/ref-17","doi-asserted-by":"publisher","first-page":"104200","DOI":"10.1016\/j.compbiomed.2020.104200","article-title":"Deep learning in spatiotemporal cardiac imaging: a review of methodologies and clinical usability","volume":"130","author":"Lara Hernandez","year":"2021","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.2506\/ref-18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.04676","article-title":"Uniformer: unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"issue":"1","key":"10.7717\/peerj-cs.2506\/ref-19","doi-asserted-by":"publisher","first-page":"106705","DOI":"10.1016\/j.compbiomed.2023.106705","article-title":"Echoefnet: multitask deep learning network for automatic calculation of left ventricular ejection fraction in 2D echocardiography","volume":"140","author":"Li","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-20","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1093\/cvr\/cvp302","article-title":"Contrast ultrasound molecular imaging of inflammation in cardiovascular disease","volume":"84","author":"Lindner","year":"2009","journal-title":"Cardiovascular Research"},{"key":"10.7717\/peerj-cs.2506\/ref-21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.14003","article-title":"EchoGNN: explainable ejection fraction estimation with graph neural networks","author":"Mokhtari","year":"2022"},{"key":"10.7717\/peerj-cs.2506\/ref-22","first-page":"370","article-title":"EchoCoTr: estimation of the left ventricular ejection fraction from spatiotemporal echocardiography","author":"Muhtaseb","year":"2022"},{"issue":"7","key":"10.7717\/peerj-cs.2506\/ref-23","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1093\/oxfordjournals.eurheartj.a015414","article-title":"The apical long-axis rather than the two-chamber view should be used in combination with the four-chamber view for accurate assessment of left ventricular volumes and function","volume":"18","author":"Nosir","year":"1997","journal-title":"European Heart Journal"},{"key":"10.7717\/peerj-cs.2506\/ref-24","first-page":"1","article-title":"Echonet-dynamic: a large new cardiac motion video data resource for medical machine learning","volume-title":"NeurIPS ML4H Workshop","author":"Ouyang","year":"2019"},{"issue":"7802","key":"10.7717\/peerj-cs.2506\/ref-25","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based ai for beat-to-beat assessment of cardiac function","volume":"580","author":"Ouyang","year":"2020","journal-title":"Nature"},{"issue":"1","key":"10.7717\/peerj-cs.2506\/ref-26","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.echo.2023.01.015","article-title":"Video-based deep learning for automated assessment of left ventricular ejection fraction in pediatric patients","volume":"36","author":"Reddy","year":"2023","journal-title":"Journal of the American Society of Echocardiography"},{"key":"10.7717\/peerj-cs.2506\/ref-27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.00977","article-title":"Ultrasound video transformers for cardiac ejection fraction estimation","author":"Reynaud","year":"2021"},{"key":"10.7717\/peerj-cs.2506\/ref-28","first-page":"5998","article-title":"Attention is all you need","author":"Shazeer","year":"2017"},{"key":"10.7717\/peerj-cs.2506\/ref-29","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4184447","article-title":"The study of echocardiography of left-ventricle segmentation combining transformer and CNN","author":"Shi","year":"2022"},{"key":"10.7717\/peerj-cs.2506\/ref-30","first-page":"123","article-title":"Ejection fraction classification in transthoracic echocardiography using a deep learning approach","author":"Silva","year":"2018"},{"issue":"24","key":"10.7717\/peerj-cs.2506\/ref-31","doi-asserted-by":"publisher","first-page":"3738","DOI":"10.1161\/CIRCULATIONAHA.105.561423","article-title":"Influence of ejection fraction on cardiovascular outcomes in a broad spectrum of heart failure patients","volume":"112","author":"Solomon","year":"2005","journal-title":"Circulation"},{"key":"10.7717\/peerj-cs.2506\/ref-32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.02549","article-title":"Light-weight spatiotemporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound","author":"Thomas","year":"2022"},{"key":"10.7717\/peerj-cs.2506\/ref-33","first-page":"6450","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"Tran","year":"2018"},{"key":"10.7717\/peerj-cs.2506\/ref-34","first-page":"319","article-title":"Dilated convolutions in neural networks for left atrial segmentation in 3D gadolinium enhanced-MRI","author":"Vesal","year":"2019"},{"key":"10.7717\/peerj-cs.2506\/ref-35","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1002\/cphy","article-title":"Biomechanics of cardiac function","volume":"5","author":"Voorhees","year":"2015","journal-title":"Comprehensive Physiology"},{"issue":"2","key":"10.7717\/peerj-cs.2506\/ref-36","doi-asserted-by":"publisher","first-page":"6","DOI":"10.36469\/00001","article-title":"Using deep learning to identify high-risk patients with heart failure with reduced ejection fraction","volume":"8","author":"Wang","year":"2021","journal-title":"Journal of Health Economics and Outcomes Research"},{"key":"10.7717\/peerj-cs.2506\/ref-37","first-page":"2530","article-title":"Early detection of heart failure with varying prediction windows by structured and unstructured data in electronic health records","author":"Wang","year":"2015"},{"key":"10.7717\/peerj-cs.2506\/ref-38","doi-asserted-by":"publisher","first-page":"102686","DOI":"10.1016\/j.media.2022.102686","article-title":"Co-learning of appearance and shape for precise ejection fraction estimation from echocardiographic sequences","volume":"84","author":"Wei","year":"2023","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.2506\/ref-39","doi-asserted-by":"publisher","first-page":"106855","DOI":"10.1016\/j.ultras.2022.106855","article-title":"MAEF-Net: multi-attention efficient feature fusion network for left ventricular segmentation and quantitative analysis in two-dimensional echocardiography","volume":"127","author":"Zeng","year":"2023","journal-title":"Ultrasonics"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2506.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2506.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2506.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2506.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T08:42:42Z","timestamp":1737448962000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,21]]},"references-count":39,"alternative-id":["10.7717\/peerj-cs.2506"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2506","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,21]]},"article-number":"e2506"}}