{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:55:27Z","timestamp":1792803327648,"version":"4.5.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NTNU Norwegian University of Science and Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>One of the main challenges in current research on segmentation in cardiac ultrasound is the lack of large and varied labeled datasets and the differences in annotation conventions between datasets. This makes it difficult to design robust segmentation models that generalize well to external datasets. This work utilizes diffusion models to create generative augmentations that can significantly improve diversity of the dataset and thus the generalisability of segmentation models without the need for more annotated data. The generative augmentations are applied in addition to regular augmentations. A visual test survey showed that experts cannot clearly distinguish between real and fully generated images. Using the proposed generative augmentations, segmentation robustness was increased when training on an internal dataset and testing on an external dataset with an improvement of over 20 millimeters in Hausdorff distance. Additionally, the limits of agreement for automatic ejection fraction (EF) estimation improved by up to 20% of absolute EF value on out of distribution cases. These improvements come exclusively from the increased variation of the training data using the generative augmentations, without modifying the underlying machine learning model.<\/jats:p>","DOI":"10.1038\/s41598-025-21938-y","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T13:25:32Z","timestamp":1761830732000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Generative augmentations for improved cardiac ultrasound segmentation using diffusion models"],"prefix":"10.1038","volume":"15","author":[{"given":"Gilles","family":"Van De Vyver","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aksel Try","family":"Lenz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Smistad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sindre Hellum","family":"Olaisen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f8rnar","family":"Grenne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Espen","family":"Holte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H\u00e5vard","family":"Dalen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lasse","family":"L\u00f8vstakken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,30]]},"reference":[{"key":"21938_CR1","unstructured":"World Health Organization. Global health estimates 2021: Deaths by cause, age, sex, by country and by region, 2000-2021 (2024)."},{"key":"21938_CR2","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1111\/echo.12832","volume":"32","author":"AC Armstrong","year":"2015","unstructured":"Armstrong, A. C. et al. Quality control and reproducibility in m-mode, two-dimensional, and speckle tracking echocardiography acquisition and analysis: the cardia study, year 25 examination experience. Echocardiography 32, 1233\u20131240 (2015).","journal-title":"Echocardiography"},{"key":"21938_CR3","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1093\/ehjci\/jev014","volume":"16","author":"RM Lang","year":"2015","unstructured":"Lang, R. M. et al. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the american society of echocardiography and the european association of cardiovascular imaging. Eur. Hear. Journal-Cardiovascular Imaging 16, 233\u2013271 (2015).","journal-title":"Eur. Hear. Journal-Cardiovascular Imaging"},{"key":"21938_CR4","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1093\/ehjci\/jead280","volume":"25","author":"S Olaisen","year":"2024","unstructured":"Olaisen, S. et al. Automatic measurements of left ventricular volumes and ejection fraction by artificial intelligence: clinical validation in real time and large databases. Eur. Hear. Journal-Cardiovascular Imaging 25, 383\u2013395 (2024).","journal-title":"Eur. Hear. Journal-Cardiovascular Imaging"},{"key":"21938_CR5","first-page":"92","volume":"qyae02","author":"J Nyberg","year":"2024","unstructured":"Nyberg, J. et al. Deep learning improves test-retest reproducibility of regional strain in echocardiography. Eur. Hear. Journal-Imaging Methods and Pract. qyae02, 92 (2024).","journal-title":"Eur. Hear. Journal-Imaging Methods and Pract."},{"key":"21938_CR6","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1016\/j.echo.2023.02.017","volume":"36","author":"IM Salte","year":"2023","unstructured":"Salte, I. M. et al. Deep learning for improved precision and reproducibility of left ventricular strain in echocardiography: a test-retest study. J. Am. Soc. Echocardiogr. 36, 788\u2013799 (2023).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"21938_CR7","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","volume":"38","author":"S Leclerc","year":"2019","unstructured":"Leclerc, S. et al. Deep learning for segmentation using an open large-scale dataset in 2d echocardiography. IEEE transactions on medical imaging 38, 2198\u20132210 (2019).","journal-title":"IEEE transactions on medical imaging"},{"key":"21938_CR8","unstructured":"Ouyang, D. et al. Echonet-dynamic: a large new cardiac motion video data resource for medical machine learning. In NeurIPS ML4H Workshop: Vancouver, BC, Canada, vol.\u00a05 (2019)."},{"key":"21938_CR9","unstructured":"Unity Imaging Collaborative. Unity imaging collaborative open-access echocardiography dataset. https:\/\/data.unityimaging.net\/. Accessed: August 27, 2025."},{"key":"21938_CR10","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3389\/fcvm.2020.00025","volume":"7","author":"C Chen","year":"2020","unstructured":"Chen, C. et al. Deep learning for cardiac image segmentation: a review. Front. cardiovascular medicine 7, 25 (2020).","journal-title":"Front. cardiovascular medicine"},{"key":"21938_CR11","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1109\/TMI.2021.3051806","volume":"40","author":"A Gilbert","year":"2021","unstructured":"Gilbert, A. et al. Generating synthetic labeled data from existing anatomical models: an example with echocardiography segmentation. IEEE Transactions on Med. Imaging 40, 2783\u20132794 (2021).","journal-title":"IEEE Transactions on Med. Imaging"},{"key":"21938_CR12","doi-asserted-by":"publisher","first-page":"98803","DOI":"10.1109\/ACCESS.2022.3207177","volume":"10","author":"C Tiago","year":"2022","unstructured":"Tiago, C. et al. A data augmentation pipeline to generate synthetic labeled datasets of 3d echocardiography images using a gan. IEEE Access 10, 98803\u201398815 (2022).","journal-title":"IEEE Access"},{"key":"21938_CR13","doi-asserted-by":"crossref","unstructured":"Stojanovski, D., Hermida, U., Lamata, P., Beqiri, A. & Gomez, A. Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation. In International Workshop on Advances in Simplifying Medical Ultrasound, 34\u201343 (Springer, 2023).","DOI":"10.1007\/978-3-031-44521-7_4"},{"key":"21938_CR14","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/s11548-020-02141-y","volume":"15","author":"MH Jafari","year":"2020","unstructured":"Jafari, M. H. et al. Cardiac point-of-care to cart-based ultrasound translation using constrained cyclegan. International journal of computer assisted radiology and surgery 15, 877\u2013886 (2020).","journal-title":"International journal of computer assisted radiology and surgery"},{"key":"21938_CR15","doi-asserted-by":"publisher","first-page":"17594","DOI":"10.1109\/ACCESS.2023.3246762","volume":"11","author":"C Tiago","year":"2023","unstructured":"Tiago, C., Snare, S. R., \u0160prem, J. & McLeod, K. A domain translation framework with an adversarial denoising diffusion model to generate synthetic datasets of echocardiography images. IEEE Access 11, 17594\u201317602 (2023).","journal-title":"IEEE Access"},{"key":"21938_CR16","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N. & Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, 2256\u20132265 (PMLR, 2015)."},{"key":"21938_CR17","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A. & Abbeel, P. Denoising diffusion probabilistic models. Advances in neural information processing systems 33, 6840\u20136851 (2020).","journal-title":"Advances in neural information processing systems"},{"key":"21938_CR18","unstructured":"Nichol, A.\u00a0Q. & Dhariwal, P. Improved denoising diffusion probabilistic models. In International conference on machine learning, 8162\u20138171 (PMLR, 2021)."},{"key":"21938_CR19","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P. & Nichol, A. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34, 8780\u20138794 (2021).","journal-title":"Advances in neural information processing systems"},{"key":"21938_CR20","unstructured":"Esan, D.\u00a0O., Owolawi, P.\u00a0A. & Tu, C. Generative adversarial networks: Applications, challenges, and open issues. intechopen (2023)."},{"key":"21938_CR21","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 234\u2013241 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21938_CR22","doi-asserted-by":"crossref","unstructured":"Lugmayr, A. et al. Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 11461\u201311471 (2022).","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"21938_CR23","doi-asserted-by":"crossref","unstructured":"Isensee, F. et al. nnu-net revisited: A call for rigorous validation in 3d medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 488\u2013498 (Springer, 2024).","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"21938_CR24","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J. & Maier-Hein, K. H. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. methods 18, 203\u2013211 (2021).","journal-title":"Nat. methods"},{"key":"21938_CR25","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1109\/TMI.2020.3003240","volume":"39","author":"N Painchaud","year":"2020","unstructured":"Painchaud, N. et al. Cardiac segmentation with strong anatomical guarantees. IEEE transactions on medical imaging 39, 3703\u20133713 (2020).","journal-title":"IEEE transactions on medical imaging"},{"key":"21938_CR26","doi-asserted-by":"crossref","unstructured":"Van De Vyver, G. et al. Towards robust cardiac segmentation using graph convolutional networks. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3373046"},{"key":"21938_CR27","doi-asserted-by":"crossref","unstructured":"Kupyn, O. & Rupprecht, C. Dataset enhancement with instance-level augmentations. In European Conference on Computer Vision, 384\u2013402 (Springer, 2025).","DOI":"10.1007\/978-3-031-73337-6_22"},{"key":"21938_CR28","doi-asserted-by":"crossref","unstructured":"Olaisen, S. et al. Automatic measurements of left ventricular volumes and ejection fraction by artificial intelligence: Clinical validation in real-time and large databases. Eur. Heart J. Cardiovasc. Imaging (2023).","DOI":"10.1093\/ehjci\/jead280"},{"key":"21938_CR29","doi-asserted-by":"publisher","first-page":"e80","DOI":"10.1093\/ije\/dyac095","volume":"52","author":"BO \u00c5svold","year":"2023","unstructured":"\u00c5svold, B. O. et al. Cohort profile update: the hunt study, norway. Int. journal epidemiology 52, e80\u2013e91 (2023).","journal-title":"Int. journal epidemiology"},{"key":"21938_CR30","unstructured":"Gazda, M., Kadoury, S., Gazda, J. & Drotar, P. Generative adversarial networks in ultrasound imaging: Extending field of view beyond conventional limits. arXiv preprint arXiv:2405.20981 (2024)."},{"key":"21938_CR31","unstructured":"Isensee, F., Jaeger, P.\u00a0F., Kohl, S.\u00a0A., Petersen, J. & Maier-Hein, K.\u00a0H. nnunet. https:\/\/github.com\/MIC-DKFZ\/nnUNet (2023)."},{"key":"21938_CR32","doi-asserted-by":"publisher","first-page":"2595","DOI":"10.1109\/TUFFC.2020.2981037","volume":"67","author":"E Smistad","year":"2020","unstructured":"Smistad, E. et al. Real-time automatic ejection fraction and foreshortening detection using deep learning. IEEE transactions on ultrasonics, ferroelectrics, and frequency control 67, 2595\u20132604 (2020).","journal-title":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control"},{"key":"21938_CR33","doi-asserted-by":"crossref","unstructured":"Fiorito, A.\u00a0M. et al. Detection of cardiac events in echocardiography using 3d convolutional recurrent neural networks. In 2018 IEEE International Ultrasonics Symposium (IUS), 1\u20134 (IEEE, 2018).","DOI":"10.1109\/ULTSYM.2018.8580137"},{"key":"21938_CR34","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1007\/s11548-015-1158-5","volume":"10","author":"E Smistad","year":"2015","unstructured":"Smistad, E., Bozorgi, M. & Lindseth, F. Fast: framework for heterogeneous medical image computing and visualization. Int. J. computer assisted radiology surgery 10, 1811\u20131822 (2015).","journal-title":"Int. J. computer assisted radiology surgery"},{"key":"21938_CR35","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B. & Hochreiter, S. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. neural information processing systems\u00a030 (2017)."},{"key":"21938_CR36","unstructured":"Salimans, T. et al. Improved techniques for training gans. Advances in neural information processing systems 29 (2016)."},{"key":"21938_CR37","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248\u2013255 (Ieee, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"21938_CR38","unstructured":"Barratt, S. & Sharma, R. A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)."},{"key":"21938_CR39","unstructured":"Rosca, M., Lakshminarayanan, B., Warde-Farley, D. & Mohamed, S. Variational approaches for auto-encoding generative adversarial networks. arXiv preprint arXiv:1706.04987 (2017)."},{"key":"21938_CR40","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R. & Simoncelli, E. P. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 600\u2013612 (2004).","journal-title":"IEEE transactions on image processing"},{"key":"21938_CR41","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J. A coefficient of agreement for nominal scales. Educ. psychological measurement 20, 37\u201346 (1960).","journal-title":"Educ. psychological measurement"},{"key":"21938_CR42","doi-asserted-by":"crossref","unstructured":"Woolson, R.\u00a0F. Wilcoxon signed-rank test. Wiley encyclopedia of clinical trials 1\u20133 (2007).","DOI":"10.1002\/9780471462422.eoct979"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21938-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21938-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21938-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T13:25:43Z","timestamp":1761830743000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21938-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,30]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["21938"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-21938-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,30]]},"assertion":[{"value":"1 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 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"}}],"article-number":"38013"}}