{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T20:35:50Z","timestamp":1779395750883,"version":"3.53.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T00:00:00Z","timestamp":1602115200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>Deep learning algorithms are increasingly used for automatic medical imaging analysis and cardiac chamber segmentation. Especially in congenital heart disease, obtaining a sufficient number of training images and data anonymity issues remain of concern.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>Progressive generative adversarial networks (PG-GAN) were trained on cardiac magnetic resonance imaging (MRI) frames from a nationwide prospective study to generate synthetic MRI frames. These synthetic frames were subsequently used to train segmentation networks (U-Net) and the quality of the synthetic training images, as well as the performance of the segmentation network was compared to U-Net-based solutions trained entirely on patient data.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>Cardiac MRI data from 303 patients with Tetralogy of Fallot were used for PG-GAN training. Using this model, we generated 100,000 synthetic images with a resolution of 256\u2009\u00d7\u2009256 pixels in 4-chamber and 2-chamber views. All synthetic samples were classified as anatomically plausible by human observers. The segmentation performance of the U-Net trained on data from 42 separate patients was statistically significantly better compared to the PG-GAN based training in an external dataset of 50 patients, however, the actual difference in segmentation quality was negligible (&lt;\u20091% in absolute terms for all models).<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Conclusion<\/jats:title>\n<jats:p>We demonstrate the utility of PG-GANs for generating large amounts of realistically looking cardiac MRI images even in rare cardiac conditions. The generated images are not subject to data anonymity and privacy concerns and can be shared freely between institutions. Training supervised deep learning segmentation networks on this synthetic data yielded similar results compared to direct training on original patient data.<\/jats:p>\n<\/jats:sec>","DOI":"10.1186\/s12880-020-00511-1","type":"journal-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T07:02:48Z","timestamp":1602140568000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Utility of deep learning networks for the generation of artificial cardiac magnetic resonance images in congenital heart disease"],"prefix":"10.1186","volume":"20","author":[{"given":"Gerhard-Paul","family":"Diller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julius","family":"Vahle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Radke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Luisa Benesch","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alicia Jeanette","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrike M. M.","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samir","family":"Sarikouch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Beerbaum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helmut","family":"Baumgartner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Orwat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"for the German Competence Network for Congenital Heart Defects Investigators","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,8]]},"reference":[{"issue":"1","key":"511_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44\u201356.","journal-title":"Nat Med"},{"issue":"8","key":"511_CR2","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","volume":"18","author":"A Hosny","year":"2018","unstructured":"Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500\u201310.","journal-title":"Nat Rev Cancer"},{"issue":"8","key":"511_CR3","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1093\/ehjci\/jey211","volume":"20","author":"G-P Diller","year":"2019","unstructured":"Diller G-P, Babu-Narayan S, Li W, Radojevic J, Kempny A, Uebing A, et al. Utility of machine learning algorithms in assessing patients with a systemic right ventricle. Eur Heart J Cardiovasc Imaging. 2019;20(8):925\u201331.","journal-title":"Eur Heart J Cardiovasc Imaging"},{"issue":"1","key":"511_CR4","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12968-018-0471-x","volume":"20","author":"W Bai","year":"2018","unstructured":"Bai W, Sinclair M, Tarroni G, et al. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson. 2018;20(1):65.","journal-title":"J Cardiovasc Magn Reson"},{"key":"511_CR5","unstructured":"Karras T, Aila T, Laine S, Lehtinen J.\u00a0Progressive growing of GANs for improved quality, stability, and variation. 2017;arXiv:1710.10196."},{"key":"511_CR6","doi-asserted-by":"publisher","unstructured":"Diller GP, Orwat S, Vahle J, et al. Prediction of prognosis in patients with tetralogy of Fallot based on deep learning imaging analysis. Heart. 2020. https:\/\/doi.org\/10.1136\/heartjnl-2019-315962.","DOI":"10.1136\/heartjnl-2019-315962"},{"key":"511_CR7","unstructured":"Volotat AK. GANs library [Internet]. 2020. pp. 1\u20132. Available from: https:\/\/github.com\/volotat\/GANLib. Accessed 07 July 2020."},{"key":"511_CR8","first-page":"5767","volume-title":"Advances in neural information processing systems","author":"I Gulrajani","year":"2017","unstructured":"Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC. Improved training of wasserstein gans. In: Advances in neural information processing systems; 2017. p. 5767\u201377."},{"issue":"22","key":"511_CR9","doi-asserted-by":"publisher","first-page":"2118","DOI":"10.1161\/CIRCULATIONAHA.115.017202","volume":"132","author":"G-P Diller","year":"2015","unstructured":"Diller G-P, Kempny A, Alonso-Gonzalez R, Swan L, Uebing A, Li W, et al. Survival prospects and circumstances of death in contemporary adult congenital heart disease patients under follow-up at a large tertiary Centre. Circulation. 2015;132(22):2118\u201325.","journal-title":"Circulation."},{"issue":"5","key":"511_CR10","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1002\/jmri.21948","volume":"30","author":"P Beerbaum","year":"2009","unstructured":"Beerbaum P, Barth P, Kropf S, Sarikouch S, Kelter-Kloepping A, Franke D, et al. Cardiac function by MRI in congenital heart disease: impact of consensus training on interinstitutional variance. J Magn Reson Imaging. 2009;30(5):956\u201366.","journal-title":"J Magn Reson Imaging"},{"issue":"6","key":"511_CR11","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1161\/CIRCIMAGING.111.963637","volume":"4","author":"S Sarikouch","year":"2011","unstructured":"Sarikouch S, Koerperich H, Dubowy K-O, Boethig D, Boettler P, Mir TS, et al. Impact of gender and age on cardiovascular function late after repair of tetralogy of Fallot: percentiles based on cardiac magnetic resonance. Circ Cardiovasc Imaging. 2011;4(6):703\u201311.","journal-title":"Circ Cardiovasc Imaging"},{"issue":"3","key":"511_CR12","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1136\/heartjnl-2015-308569","volume":"102","author":"S Orwat","year":"2016","unstructured":"Orwat S, Diller G-P, Kempny A, Radke R, Peters B, K\u00fchne T, et al. Myocardial deformation parameters predict outcome in patients with repaired tetralogy of Fallot. Heart. 2016;102(3):209\u201315.","journal-title":"Heart."},{"key":"511_CR13","first-page":"234","volume-title":"U-net: convolutional networks for biomedical image segmentation","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Cham: Springer International Publishing; 2015. p. 234\u201341."},{"issue":"16","key":"511_CR14","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","volume":"138","author":"J Zhang","year":"2018","unstructured":"Zhang J, Gajjala S, Agrawal P, Tison GH, Hallock LA, Beussink-Nelson L, et al. Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation. 2018;138(16):1623\u201335.","journal-title":"Circulation."},{"key":"511_CR15","doi-asserted-by":"crossref","unstructured":"Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, Rueckert D.\u00a0Deep learning for cardiac image segmentation: a review. 2019. arXiv:191103723. arXiv preprint.","DOI":"10.3389\/fcvm.2020.00025"},{"key":"511_CR16","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y.\u00a0Generative adversarial nets. In:\u00a0Advances in neural information processing systems. 2014;2014:2672\u201380."},{"key":"511_CR17","doi-asserted-by":"publisher","first-page":"101698","DOI":"10.1016\/j.compmedimag.2020.101698","volume":"80","author":"M Zhao","year":"2020","unstructured":"Zhao M, Liu X, Liu H, Wong KKL. Super-resolution of cardiac magnetic resonance images using Laplacian pyramid based on generative adversarial networks. Comput Med Imaging Graph. 2020;80:101698.","journal-title":"Comput Med Imaging Graph"},{"issue":"12","key":"511_CR18","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1007\/s10554-019-01671-0","volume":"35","author":"G-P Diller","year":"2019","unstructured":"Diller G-P, Lammers AE, Babu-Narayan S, Li W, Radke RM, Baumgartner H, et al. Denoising and artefact removal for transthoracic echocardiographic imaging in congenital heart disease: utility of diagnosis specific deep learning algorithms. Int J Cardiovasc Imaging. 2019;35(12):2189\u201396.","journal-title":"Int J Cardiovasc Imaging"},{"issue":"10","key":"511_CR19","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.3390\/s19102361","volume":"19","author":"C-B Jin","year":"2019","unstructured":"Jin C-B, Kim H, Liu M, Jung W, Joo S, Park E, et al. Deep CT to MR synthesis using paired and unpaired data. Sensors (Basel). 2019;19(10):2361.","journal-title":"Sensors (Basel)"},{"key":"511_CR20","first-page":"1","volume-title":"Medical image synthesis for data augmentation and anonymization using generative adversarial networks","author":"HC Shin","year":"2018","unstructured":"Shin HC, Tenenholtz NA, Rogers JK, Schwarz CG, Senjem ML, Gunter JL, et al. Medical image synthesis for data augmentation and anonymization using generative adversarial networks. Cham: Springer International Publishing; 2018. p. 1\u201311."}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-020-00511-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-020-00511-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-020-00511-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T19:50:51Z","timestamp":1633636251000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-020-00511-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,8]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["511"],"URL":"https:\/\/doi.org\/10.1186\/s12880-020-00511-1","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,8]]},"assertion":[{"value":"7 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Patients formed part of a prospective nationwide study initiated and conducted by the Investigators of the German Competence Network for Congenital Heart Defects between 2003 and 2009 (Follow up of Post- Repair Tetralogy of Fallot; ; unique identifier, NCT00266188). All study participants (or their legal representatives) gave written informed consent before the baseline MRI investigation and study inclusion, which were approved by the Ethics Committee (Ruhr University Bochum, Bad Oeynhausen, Germany, Reg.-No. 14\/03).","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"113"}}