{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:39:33Z","timestamp":1772649573910,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T00:00:00Z","timestamp":1742601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Else Kr\u00f6ner Fresenius Center for Digital Health"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>High-quality image data is essential for training deep learning (DL) classifiers, yet data sharing is often limited by privacy concerns. We hypothesized that generative adversarial networks (GANs) could synthesize bone marrow smear (BMS) images suitable for classifier training. BMS from 1251 patients with acute myeloid leukemia (AML), 51 patients with acute promyelocytic leukemia (APL), and 236 stem cell donors were digitized, and synthetic images were generated using StyleGAN2-Ada. In a blinded visual Turing test, eight hematologists achieved 63% accuracy in identifying synthetic images, confirming high image quality. DL classifiers trained on real data achieved AUROCs of 0.99 across AML, APL, and donor classifications, with performance remaining above 0.95 even when incrementally substituting real data for synthetic samples. Adding synthetic data to real training data offered performance gains for an exceptionally rare disease (APL). Our study demonstrates the usability of synthetic BMS data for training highly accurate image classifiers in microscopy.<\/jats:p>","DOI":"10.1038\/s41746-025-01563-9","type":"journal-article","created":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T01:39:06Z","timestamp":1742607546000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Synthetic bone marrow images augment real samples in developing acute myeloid leukemia microscopy classification models"],"prefix":"10.1038","volume":"8","author":[{"given":"Jan-Niklas","family":"Eckardt","sequence":"first","affiliation":[]},{"given":"Ishan","family":"Srivastava","sequence":"additional","affiliation":[]},{"given":"Zizhe","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Susann","family":"Winter","sequence":"additional","affiliation":[]},{"given":"Tim","family":"Schmittmann","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Riechert","sequence":"additional","affiliation":[]},{"given":"Miriam Eva Helena","family":"Gediga","sequence":"additional","affiliation":[]},{"given":"Anas Shekh","family":"Sulaiman","sequence":"additional","affiliation":[]},{"given":"Martin M. K.","family":"Schneider","sequence":"additional","affiliation":[]},{"given":"Freya","family":"Schulze","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Thiede","sequence":"additional","affiliation":[]},{"given":"Katja","family":"Sockel","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Kroschinsky","sequence":"additional","affiliation":[]},{"given":"Christoph","family":"R\u00f6llig","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Bornh\u00e4user","sequence":"additional","affiliation":[]},{"given":"Karsten","family":"Wendt","sequence":"additional","affiliation":[]},{"given":"Jan Moritz","family":"Middeke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,22]]},"reference":[{"key":"1563_CR1","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 https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2018\/7068349 (Wiley Ltd, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1563_CR2","doi-asserted-by":"publisher","first-page":"7068349","DOI":"10.1155\/2018\/7068349","volume":"2018","author":"A Voulodimos","year":"2018","unstructured":"Voulodimos, A., Doulamis, N., Doulamis, A. & Protopapadakis, E. Deep learning for computer vision: a brief review. Comput. Intell. Neurosci 2018, 7068349 (2018).","journal-title":"Comput. Intell. Neurosci"},{"key":"1563_CR3","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","volume":"9","author":"R Yamashita","year":"2018","unstructured":"Yamashita, R., Nishio, M., Do, R. K. G. & Togashi, K. Convolutional neural networks: an overview and application in radiology. Insights Imaging 9, 611\u2013629 (2018).","journal-title":"Insights Imaging"},{"key":"1563_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data 6, 60 (2019).","journal-title":"J. Big Data"},{"key":"1563_CR5","doi-asserted-by":"publisher","unstructured":"Goodfellow, I. J. et al. Generative adversarial networks. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1406.2661 (2014).","DOI":"10.48550\/arXiv.1406.2661"},{"key":"1563_CR6","unstructured":"Osuala, R. et al. A review of generative adversarial networks in cancer imaging: new applications, new solutions. ArXiv https:\/\/arxiv.org\/abs\/2107.09543 (2021)."},{"key":"1563_CR7","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41375-021-01408-w","volume":"36","author":"J-N Eckardt","year":"2022","unstructured":"Eckardt, J.-N. et al. Deep learning detects acute myeloid leukemia and predicts NPM1 mutation status from bone marrow smears. Leukemia 36, 111\u2013118 (2022).","journal-title":"Leukemia"},{"key":"1563_CR8","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-022-09307-8","volume":"22","author":"J-N Eckardt","year":"2022","unstructured":"Eckardt, J.-N. et al. Deep learning identifies acute promyelocytic leukemia in bone marrow smears. BMC Cancer 22, 201 (2022).","journal-title":"BMC Cancer"},{"key":"1563_CR9","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. High-Resolution image synthesis with latent diffusion models. in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 10674\u201310685 (2022).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1563_CR10","unstructured":"Ramesh, A. et al. Zero-shot text-to-image generation. in Proceedings of the 38th International Conference on Machine Learning 8821\u20138831 (PMLR, 2021)."},{"key":"1563_CR11","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1016\/j.jacr.2020.04.007","volume":"17","author":"E Lotan","year":"2020","unstructured":"Lotan, E. et al. Medical imaging and privacy in the era of artificial intelligence: myth, fallacy, and the future. J. Am. Coll. Radiol. 17, 1159\u20131162 (2020).","journal-title":"J. Am. Coll. Radiol."},{"key":"1563_CR12","doi-asserted-by":"publisher","first-page":"101552","DOI":"10.1016\/j.media.2019.101552","volume":"58","author":"X Yi","year":"2019","unstructured":"Yi, X., Walia, E. & Babyn, P. Generative adversarial network in medical imaging: a review. Med. Image Anal. 58, 101552 (2019).","journal-title":"Med. Image Anal."},{"key":"1563_CR13","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4103\/jpi.jpi_103_20","volume":"12","author":"L Jose","year":"2021","unstructured":"Jose, L., Liu, S., Russo, C., Nadort, A. & Di Ieva, A. Generative adversarial networks in digital pathology and histopathological image processing: a review. J. Pathol. Inf. 12, 43 (2021).","journal-title":"J. Pathol. Inf."},{"key":"1563_CR14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23081-4","volume":"12","author":"F Prezja","year":"2022","unstructured":"Prezja, F., Paloneva, J., P\u00f6l\u00f6nen, I., Niinim\u00e4ki, E. & \u00c4yr\u00e4m\u00f6, S. DeepFake knee osteoarthritis X-rays from generative adversarial neural networks deceive medical experts and offer augmentation potential to automatic classification. Sci. Rep. 12, 18573 (2022).","journal-title":"Sci. Rep."},{"key":"1563_CR15","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1038\/s42256-022-00560-x","volume":"4","author":"T Han","year":"2022","unstructured":"Han, T. et al. Image prediction of disease progression for osteoarthritis by style-based manifold extrapolation. Nat. Mach. Intell. 4, 1029\u20131039 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"1563_CR16","doi-asserted-by":"publisher","unstructured":"Bain, B. J., Clark, D. M. & Wilkins, B. S. Special techniques applicable to bone marrow diagnosis. In Bone Marrow Pathology (eds, Bain B. J., Clark D. M. & Wilkins B. S.). https:\/\/doi.org\/10.1002\/9781119398929.ch2 (2019).","DOI":"10.1002\/9781119398929.ch2"},{"key":"1563_CR17","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1056\/NEJMra043442","volume":"353","author":"BJ Bain","year":"2005","unstructured":"Bain, B. J. Diagnosis from the blood smear. N. Engl. J. Med. 353, 498\u2013507 (2005).","journal-title":"N. Engl. J. Med."},{"key":"1563_CR18","doi-asserted-by":"publisher","first-page":"107314","DOI":"10.1016\/j.cmpb.2022.107314","volume":"229","author":"K Barrera","year":"2023","unstructured":"Barrera, K., Merino, A., Molina, A. & Rodellar, J. Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan). Comput. Methods Prog. Biomed.229, 107314 (2023).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"1563_CR19","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.procs.2021.02.101","volume":"183","author":"K Liu","year":"2021","unstructured":"Liu, K., Shuai, R., Ma, L. & ZeXu Cells image generation method based on VAE-SGAN. Procedia Comput. Sci. 183, 589\u2013595 (2021).","journal-title":"Procedia Comput. Sci."},{"key":"1563_CR20","doi-asserted-by":"publisher","first-page":"276","DOI":"10.3390\/biology11020276","volume":"11","author":"D Hazra","year":"2022","unstructured":"Hazra, D., Byun, Y.-C., Kim, W. J. & Kang, C.-U. Synthesis of microscopic cell images obtained from bone marrow aspirate smears through generative adversarial networks. Biology 11, 276 (2022).","journal-title":"Biology"},{"key":"1563_CR21","doi-asserted-by":"publisher","first-page":"107019","DOI":"10.1016\/j.cmpb.2022.107019","volume":"224","author":"D Hazra","year":"2022","unstructured":"Hazra, D., Byun, Y.-C. & Kim, W. J. Enhancing classification of cells procured from bone marrow aspirate smears using generative adversarial networks and sequential convolutional neural network. Comput. Methods Prog. Biomed. 224, 107019 (2022).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"1563_CR22","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","volume":"43","author":"T Karras","year":"2021","unstructured":"Karras, T., Laine, S. & Aila, T. A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43, 4217\u20134228 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1563_CR23","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1182\/blood-2010-01-267302","volume":"116","author":"C R\u00f6llig","year":"2010","unstructured":"R\u00f6llig, C. et al. A novel prognostic model in elderly patients with acute myeloid leukemia: results of 909 patients entered into the prospective AML96 trial. Blood 116, 971\u2013978 (2010).","journal-title":"Blood"},{"key":"1563_CR24","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.1200\/JCO.2012.46.4743","volume":"31","author":"M Schaich","year":"2013","unstructured":"Schaich, M. et al. High-dose cytarabine consolidation with or without additional amsacrine and mitoxantrone in acute myeloid leukemia: results of the prospective randomized AML2003 trial. J. Clin. Oncol. 31, 2094\u20132102 (2013).","journal-title":"J. Clin. Oncol."},{"key":"1563_CR25","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1093\/annonc\/mdy030","volume":"29","author":"C R\u00f6llig","year":"2018","unstructured":"R\u00f6llig, C. et al. Intermediate-dose cytarabine plus mitoxantrone versus standard-dose cytarabine plus daunorubicin for acute myeloid leukemia in elderly patients. Ann. Oncol. 29, 973\u2013978 (2018).","journal-title":"Ann. Oncol."},{"key":"1563_CR26","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1016\/S1470-2045(15)00362-9","volume":"16","author":"C R\u00f6llig","year":"2015","unstructured":"R\u00f6llig, C. et al. Addition of sorafenib versus placebo to standard therapy in patients aged 60 years or younger with newly diagnosed acute myeloid leukaemia (SORAML): a multicentre, phase 2, randomised controlled trial. Lancet Oncol. 16, 1691\u20131699 (2015).","journal-title":"Lancet Oncol."},{"key":"1563_CR27","doi-asserted-by":"publisher","first-page":"2723","DOI":"10.1007\/s00277-020-04255-4","volume":"99","author":"S Parmentier","year":"2020","unstructured":"Parmentier, S. et al. Reevaluation of reference values for bone marrow differential counts in 236 healthy bone marrow donors. Ann. Hematol. 99, 2723\u20132729 (2020).","journal-title":"Ann. Hematol."},{"key":"1563_CR28","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1001\/jama.2013.281053","volume":"310","author":"World Medical Association.","year":"2013","unstructured":"World Medical Association. World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA 310, 2191\u20132194 (2013).","journal-title":"JAMA"},{"key":"1563_CR29","doi-asserted-by":"publisher","unstructured":"Karras, T. et al. Training generative adversarial networks with limited data. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2006.06676 (2020).","DOI":"10.48550\/arXiv.2006.06676"},{"key":"1563_CR30","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: a next-generation hyperparameter optimization framework. in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2623\u20132631 (Association for Computing Machinery, 2019).","DOI":"10.1145\/3292500.3330701"},{"key":"1563_CR31","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 Trans. Image Process. 13, 600\u2013612 (2004).","journal-title":"IEEE Trans. Image Process."},{"key":"1563_CR32","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1073\/pnas.1422953112","volume":"112","author":"D Geman","year":"2015","unstructured":"Geman, D., Geman, S., Hallonquist, N. & Younes, L. Visual Turing test for computer vision systems. Proc. Natl. Acad. Sci. USA 112, 3618\u20133623 (2015).","journal-title":"Proc. Natl. Acad. Sci. USA"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01563-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01563-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01563-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T01:39:14Z","timestamp":1742607554000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01563-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,22]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1563"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01563-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,22]]},"assertion":[{"value":"29 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"173"}}