{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T13:32:47Z","timestamp":1791639167389,"version":"4.3.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Institute of Biomedical Imaging And Bioengineering of the National Institutes of Health","award":["T32EB025766"],"award-info":[{"award-number":["T32EB025766"]}]},{"DOI":"10.13039\/100000049","name":"National Institute On Aging","doi-asserted-by":"crossref","award":["R21AG055954"],"award-info":[{"award-number":["R21AG055954"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Cardiovasc Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Real time 2D phase contrast (RTPC) MRI is useful for flow quantification in atrial fibrillation (AF) patients, but data analysis requires time-consuming anatomical contouring for many cardiac time frames. Our goal was to develop a convolutional neural network (CNN) for fully automated left atrial (LA) flow quantification. Forty-four AF patients underwent cardiac MRI including LA RTPC, collecting a median of 358 timeframes per scan. 15,307 semi-manual derived RTPC LA contours comprised ground truth for CNN training, validation, and testing. CNN vs. human performance was assessed using Dice scores (DSC), Hausdorff distance (HD), and flow measures (stasis, velocities, flow). LA contour DSC across all patients were similar to human inter-observer DSC (0.90 vs. 0.93) and a median 4.6\u00a0mm [3.5\u20135.9\u00a0mm] HD. There was no impact of heart rate variability on contouring quality (low vs. high variability DSC: 0.92\u2009\u00b1\u20090.05 vs. 0.91\u2009\u00b1\u20090.03, <jats:italic>p<\/jats:italic>\u2009=\u20090.95). CNN based LA flow quantification showed good to excellent agreement with semi-manual analysis (<jats:italic>r<\/jats:italic>\u2009&gt;\u20090.90) and small bias in Bland-Altman analysis for mean velocity (-0.10\u00a0cm\/s), stasis (1%), and net flow (-2.4\u00a0ml\/s). This study demonstrated the feasibility of CNN based LA flow analysis with good agreements in LA contours and flow measures and resilience to heartbeat variability in AF.<\/jats:p>","DOI":"10.1007\/s10554-025-03407-9","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T16:45:27Z","timestamp":1745945127000},"page":"1197-1208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation"],"prefix":"10.1007","volume":"41","author":[{"given":"Justin","family":"Baraboo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amanda","family":"DiCarlo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haben","family":"Berhane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daming","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rod","family":"Passman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel C.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick M.","family":"McCarthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rishi","family":"Arora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Markl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"3407_CR1","doi-asserted-by":"publisher","unstructured":"Gatehouse PD et al (2005) Applications of phase-contrast flow and velocity imaging in cardiovascular MRI. European Radiology vol. 15 2172\u20132184 Preprint at https:\/\/doi.org\/10.1007\/s00330-005-2829-3","DOI":"10.1007\/s00330-005-2829-3"},{"key":"3407_CR2","doi-asserted-by":"publisher","first-page":"662","DOI":"10.2214\/AJR.07.3744","volume":"192","author":"MB Srichai","year":"2009","unstructured":"Srichai MB, Lim RP, Wong S, Lee VS (2009) Cardiovascular applications of Phase-Contrast MRI. Am J Roentgenol 192:662\u2013675","journal-title":"Am J Roentgenol"},{"key":"3407_CR3","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s12968-020-00607-1","volume":"22","author":"CM Kramer","year":"2020","unstructured":"Kramer CM et al (2020) Standardized cardiovascular magnetic resonance imaging (CMR) protocols: 2020 update. J Cardiovasc Magn Reson 22:17","journal-title":"J Cardiovasc Magn Reson"},{"key":"3407_CR4","doi-asserted-by":"publisher","unstructured":"Garg P et al (2020) Assessment of mitral valve regurgitation by cardiovascular magnetic resonance imaging. Nature Reviews Cardiology vol. 17 298\u2013312 Preprint at https:\/\/doi.org\/10.1038\/s41569-019-0305-z","DOI":"10.1038\/s41569-019-0305-z"},{"key":"3407_CR5","doi-asserted-by":"publisher","unstructured":"Powell AJ, Geva T (2000) Blood flow measurement by magnetic resonance imaging in congenital heart disease. Pediatric Cardiology vol. 21 47\u201358 Preprint at https:\/\/doi.org\/10.1007\/s002469910007","DOI":"10.1007\/s002469910007"},{"key":"3407_CR6","doi-asserted-by":"publisher","first-page":"W107","DOI":"10.2214\/AJR.05.0219","volume":"187","author":"KW Neff","year":"2006","unstructured":"Neff KW, Horn P, Schmiedek P, D\u00fcber C, Dinter DJ (2006) 2D cine Phase-Contrast MRI for volume flow evaluation of the Brain-Supplying circulation in Moyamoya disease. Am J Roentgenol 187:W107\u2013W115","journal-title":"Am J Roentgenol"},{"key":"3407_CR7","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3233\/THC-2008-16206","volume":"16","author":"C Karmonik","year":"2008","unstructured":"Karmonik C, Klucznik R, Benndorf G (2008) Comparison of velocity patterns in an AComA aneurysm measured with 2D phase contrast MRI and simulated with CFD. Technol Health Care 16:119\u2013128","journal-title":"Technol Health Care"},{"key":"3407_CR8","first-page":"204800401773198","volume":"6","author":"J Sotelo","year":"2017","unstructured":"Sotelo J et al (2017) Quantification of pulmonary regurgitation in patients with repaired tetralogy of fallot by 2D phase-contrast MRI: differences between the standard method of velocity averaging and a pixel-wise analysis. JRSM Cardiovasc Dis 6:204800401773198","journal-title":"JRSM Cardiovasc Dis"},{"key":"3407_CR9","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1016\/j.echo.2005.05.006","volume":"18","author":"M Handke","year":"2005","unstructured":"Handke M et al (2005) Left atrial appendage flow velocity as a quantitative surrogate parameter for thromboembolic risk: determinants and relationship to spontaneous Echocontrast and Thrombus Formation\u2013A transesophageal echocardiographic study in 500 patients with cerebral ischemia. J Am Soc Echocardiogr 18:1366\u20131372","journal-title":"J Am Soc Echocardiogr"},{"key":"3407_CR10","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1016\/S0735-1097(98)00146-6","volume":"31","author":"M Zabalgoitia","year":"1998","unstructured":"Zabalgoitia M et al (1998) Transesophageal echocardiographic correlates of clinical risk of thromboembolism in nonvalvular atrial fibrillation. J Am Coll Cardiol 31:1622\u20131626","journal-title":"J Am Coll Cardiol"},{"key":"3407_CR11","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1002\/jmri.1880050606","volume":"5","author":"AC Eichenberger","year":"1995","unstructured":"Eichenberger AC, Schwitter J, McKinnon GC, Debatin JF, Von Schulthess GK (1995) Phase-contrast echo-planar MR imaging: Real-time quantification of plow and velocity patterns in the thoracic vessels induced by Valsalva\u2019s maneuver. J Magn Reson Imaging 5:648\u2013655","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR12","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.neuroimage.2015.07.073","volume":"122","author":"L Chen","year":"2015","unstructured":"Chen L, Beckett A, Verma A, Feinberg DA (2015) Dynamics of respiratory and cardiac CSF motion revealed with real-time simultaneous multi-slice EPI velocity phase contrast imaging. NeuroImage 122:281\u2013287","journal-title":"NeuroImage"},{"key":"3407_CR13","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1148\/radiol.2213010455","volume":"221","author":"A Shankaranarayanan","year":"2001","unstructured":"Shankaranarayanan A, Simonetti OP, Laub G, Lewin JS, Duerk JL (2001) Segmented k-space and real-time cardiac cine MR imaging with radial trajectories. Radiology 221:827\u2013836","journal-title":"Radiology"},{"key":"3407_CR14","doi-asserted-by":"publisher","first-page":"e4240","DOI":"10.1002\/nbm.4240","volume":"33","author":"H Haji-Valizadeh","year":"2020","unstructured":"Haji-Valizadeh H et al (2020) Highly accelerated, real\u2010time phase\u2010contrast MRI using radial k \u2010space sampling and GROG\u2010GRASP reconstruction: a feasibility study in pediatric patients with congenital heart disease. NMR Biomed 33:e4240","journal-title":"NMR Biomed"},{"key":"3407_CR15","doi-asserted-by":"publisher","unstructured":"Nayak KS, Pauly JM, Kerr AB, Hu BS, Nishimura DG (2000) Real-Time color flow MRI. https:\/\/doi.org\/10.1002\/(SICI)1522-2594(200002)43:2%3C251::AID-MRM12%3E3.0.CO;2-","DOI":"10.1002\/(SICI)1522-2594(200002)43:2%3C251::AID-MRM12%3E3.0.CO;2-"},{"key":"3407_CR16","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1002\/mrm.21391","volume":"58","author":"M Lustig","year":"2007","unstructured":"Lustig M, Donoho D, Pauly JM, Sparse MRI (2007) The application of compressed sensing for rapid MR imaging. Magn Reson Med 58:1182\u20131195","journal-title":"Magn Reson Med"},{"key":"3407_CR17","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1002\/jmri.24328","volume":"40","author":"A Joseph","year":"2014","unstructured":"Joseph A et al (2014) Real-time flow MRI of the aorta at a resolution of 40 Msec. J Magn Reson Imaging 40:206\u2013213","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR18","doi-asserted-by":"crossref","unstructured":"Kowallick JT et al (2014) Real-time phase-contrast flow MRI of the ascending aorta and superior Vena Cava as a function of intrathoracic pressure (Valsalva manoeuvre). Br J Radiol 87","DOI":"10.1259\/bjr.20140401"},{"key":"3407_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12968-018-0471-x","volume":"20","author":"W Bai","year":"2018","unstructured":"Bai W et al (2018) Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 20:65","journal-title":"J Cardiovasc Magn Reson"},{"key":"3407_CR20","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1109\/TMI.2018.2820742","volume":"37","author":"Q Zheng","year":"2018","unstructured":"Zheng Q, Delingette H, Duchateau N, Ayache N (2018) 3-D consistent and robust segmentation of cardiac images by deep learning with Spatial propagation. IEEE Trans Med Imaging 37:2137\u20132148","journal-title":"IEEE Trans Med Imaging"},{"key":"3407_CR21","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.media.2018.10.004","volume":"51","author":"M Khened","year":"2019","unstructured":"Khened M, Kollerathu VA, Krishnamurthi G (2019) Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers. Med Image Anal 51:21\u201345","journal-title":"Med Image Anal"},{"key":"3407_CR22","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1002\/mrm.27030","volume":"80","author":"T Benkert","year":"2018","unstructured":"Benkert T et al (2018) Optimization and validation of accelerated golden-angle radial sparse MRI reconstruction with self-calibrating GRAPPA operator gridding. Magn Reson Med 80:286\u2013293","journal-title":"Magn Reson Med"},{"key":"3407_CR23","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"3D U-Net: learning dense volumetric segmentation from sparse annotation","author":"\u00d6 \u00c7i\u00e7ek","year":"2016","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. Springer, Cham, pp 424\u2013432. https:\/\/doi.org\/10.1007\/978-3-319-46723-8_49"},{"key":"3407_CR24","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, van der Maaten L, Weinberger KQ (2016) Densely Connected Convolutional Networks","DOI":"10.1109\/CVPR.2017.243"},{"key":"3407_CR25","doi-asserted-by":"publisher","first-page":"2204","DOI":"10.1002\/mrm.28257","volume":"84","author":"H Berhane","year":"2020","unstructured":"Berhane H et al (2020) Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning. Magn Reson Med 84:2204\u20132218","journal-title":"Magn Reson Med"},{"key":"3407_CR26","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1097\/RLI.0000000000000219","volume":"51","author":"M Markl","year":"2016","unstructured":"Markl M et al (2016) Left atrial 4-Dimensional flow magnetic resonance imaging: stasis and velocity mapping in patients with atrial fibrillation. Invest Radiol 51:147\u2013154","journal-title":"Invest Radiol"},{"key":"3407_CR27","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/BF02345439","volume":"39","author":"K Tateno","year":"2001","unstructured":"Tateno K, Glass L (2001) Automatic detection of atrial fibrillation using the coefficient of variation and density histograms of RR and \u2206RR intervals. Med Biol Eng Comput 39:664\u2013671","journal-title":"Med Biol Eng Comput"},{"key":"3407_CR28","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1002\/jmri.22402","volume":"33","author":"F Odille","year":"2011","unstructured":"Odille F, Steeden JA, Muthurangu V, Atkinson D (2011) Automatic segmentation propagation of the aorta in real-time phase contrast MRI using nonrigid registration. J Magn Reson Imaging 33:232\u2013238","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR29","doi-asserted-by":"publisher","DOI":"10.1002\/JMRI.29702","author":"T Lala","year":"2025","unstructured":"Lala T et al (2025) Evaluation of Real-Time cardiovascular flow MRI using compressed sensing in a Phantom and in patients with valvular disease or arrhythmia. J Magn Reson Imaging. https:\/\/doi.org\/10.1002\/JMRI.29702","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12968-018-0509-0","volume":"21","author":"A Bratt","year":"2019","unstructured":"Bratt A et al (2019) Machine learning derived segmentation of phase velocity encoded cardiovascular magnetic resonance for fully automated aortic flow quantification. J Cardiovasc Magn Reson 21:1","journal-title":"J Cardiovasc Magn Reson"},{"key":"3407_CR31","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1002\/jmri.22124","volume":"31","author":"A Herment","year":"2010","unstructured":"Herment A et al (2010) Automated segmentation of the aorta from phase contrast MR images: validation against expert tracing in healthy volunteers and in patients with a dilated aorta. J Magn Reson Imaging 31:881\u2013888","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR32","doi-asserted-by":"publisher","first-page":"86","DOI":"10.3389\/fcvm.2020.00086","volume":"7","author":"K Jamart","year":"2020","unstructured":"Jamart K, Xiong Z, Maso Talou GD, Stiles MK, Zhao J (2020) Mini review: deep learning for atrial segmentation from late Gadolinium-Enhanced MRIs. Front Cardiovasc Med 7:86","journal-title":"Front Cardiovasc Med"},{"key":"3407_CR33","doi-asserted-by":"publisher","first-page":"101916","DOI":"10.1016\/j.media.2020.101916","volume":"68","author":"X Zhang","year":"2021","unstructured":"Zhang X, Noga M, Martin DG, Punithakumar K (2021) Fully automated left atrium segmentation from anatomical cine long-axis MRI sequences using deep convolutional neural network with unscented Kalman filter. Med Image Anal 68:101916","journal-title":"Med Image Anal"},{"key":"3407_CR34","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1161\/01.CIR.0000126494.66859.A2","volume":"109","author":"H K\u00f6rperich","year":"2004","unstructured":"K\u00f6rperich H et al (2004) Flow volume and shunt quantification in pediatric congenital heart disease by Real-Time magnetic resonance velocity mapping: A validation study. Circulation 109:1987\u20131993","journal-title":"Circulation"},{"key":"3407_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/MRM.30399","author":"H Yang","year":"2024","unstructured":"Yang H et al (2024) Aortic velocity measurements derived from phase-contrast MRI are influenced by a cardiac implantable electronic device in both adult and pediatric human subjects. Magn Reson Med. https:\/\/doi.org\/10.1002\/MRM.30399","journal-title":"Magn Reson Med"},{"key":"3407_CR36","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1002\/jmri.28550","volume":"58","author":"AL DiCarlo","year":"2023","unstructured":"DiCarlo AL et al (2023) Assessment of Beat-To-Beat variability in left atrial hemodynamics using real time phase contrast MRI in patients with atrial fibrillation. J Magn Reson Imaging 58:763\u2013771","journal-title":"J Magn Reson Imaging"},{"key":"3407_CR37","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1016\/j.jacbts.2019.05.005","volume":"4","author":"MJ Shen","year":"2019","unstructured":"Shen MJ, Arora R, Jalife J (2019) Atrial myopathy. JACC Basic Transl Sci 4:640\u2013654","journal-title":"JACC Basic Transl Sci"},{"key":"3407_CR38","doi-asserted-by":"publisher","first-page":"61","DOI":"10.15420\/aer.2020.13","volume":"9","author":"H Rivner","year":"2020","unstructured":"Rivner H, Mitrani RD, Goldberger JJ (2020) Atrial myopathy underlying atrial fibrillation. Arrhythm Electrophysiol Rev 9:61\u201370","journal-title":"Arrhythm Electrophysiol Rev"},{"key":"3407_CR39","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1002\/jmri.27581","volume":"54","author":"J Jang","year":"2021","unstructured":"Jang J et al (2021) Sensitivity of myocardial radiomic features to imaging parameters in cardiac MR imaging. J Magn Reson Imaging 54:787\u2013794","journal-title":"J Magn Reson Imaging"}],"container-title":["The International Journal of Cardiovascular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-025-03407-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10554-025-03407-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10554-025-03407-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T10:34:40Z","timestamp":1749724480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10554-025-03407-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,29]]},"references-count":39,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["3407"],"URL":"https:\/\/doi.org\/10.1007\/s10554-025-03407-9","relation":{},"ISSN":["1875-8312"],"issn-type":[{"value":"1875-8312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,29]]},"assertion":[{"value":"7 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}