{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:40:06Z","timestamp":1792813206763,"version":"4.5.0"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e4tsklinikum Carl Gustav Carus Dresden an der Technischen Universit\u00e4t Dresden"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Hematol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate differentiation of BCR::ABL1-negative myeloproliferative neoplasms (MPNs) based on bone marrow smear morphology remains challenging. While previous artificial intelligence (AI) approaches have primarily focused on bone marrow core biopsies, the diagnostic potential of routine bone marrow smears has remained largely unexplored. Using 460 digitized bone marrow smear whole-slide images, we developed an attention-based multi-instance learning model using features extracted from a self-supervised vision foundation model to classify polycythemia vera (PV), essential thrombocythemia (ET), and primary myelofibrosis (PMF) and to predict\n                    <jats:italic>JAK2<\/jats:italic>\n                    and\n                    <jats:italic>CALR<\/jats:italic>\n                    mutation status. Our model achieved a receiver-operating-characteristic area-under-the-curve (ROC-AUC) of 0.84 for MPN subtype classification and predicted\n                    <jats:italic>JAK2<\/jats:italic>\n                    and\n                    <jats:italic>CALR<\/jats:italic>\n                    mutation status in ET (ROC-AUC 0.73 and 0.75) and PMF (ROC-AUC 0.67 and 0.70) based on bone marrow smear images only. Our results provide a proof of-concept for AI-supported bone marrow cytomorphology as a modality complementary to core biopsies in MPN diagnostics and suggest that driver mutations leave traceable morphological signatures in smears. Multimodal integration of microscopic imaging with laboratory and clinical findings may further boost MPN differentiation performance of diagnostic AI models.\n                  <\/jats:p>","DOI":"10.1007\/s00277-026-07257-w","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T09:37:02Z","timestamp":1787650622000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning differentiates myeloproliferative neoplasms and predicts JAK2 and CALR mutations from bone marrow smears"],"prefix":"10.1007","volume":"105","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3649-2823","authenticated-orcid":false,"given":"Jan-Niklas","family":"Eckardt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chethan Babu V.","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Hauspurg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Riechert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Schmittmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ishan","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susann","family":"Winter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katja","family":"Sockel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Badst\u00fcbner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Bornh\u00e4user","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Tiemann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan Moritz","family":"Middeke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"issue":"22","key":"7257_CR1","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.1056\/NEJMra1406186","volume":"376","author":"JL Spivak","year":"2017","unstructured":"Spivak JL (2017) Myeloproliferative Neoplasms. N Engl J Med 376(22):2168\u20132181. https:\/\/doi.org\/10.1056\/NEJMra1406186","journal-title":"N Engl J Med"},{"issue":"11","key":"7257_CR2","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1182\/blood.2022015850","volume":"140","author":"DA Arber","year":"2022","unstructured":"Arber DA, Orazi A, Hasserjian RP et al (2022) International Consensus Classification of Myeloid Neoplasms and Acute Leukemias: integrating morphologic, clinical, and genomic data. Blood 140(11):1200\u20131228. https:\/\/doi.org\/10.1182\/blood.2022015850","journal-title":"Blood"},{"issue":"7","key":"7257_CR3","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1038\/s41375-022-01613-1","volume":"36","author":"JD Khoury","year":"2022","unstructured":"Khoury JD, Solary E, Abla O et al (2022) The 5th edition of the World Health Organization Classification of Haematolymphoid Tumours: Myeloid and Histiocytic\/Dendritic Neoplasms. Leukemia 36(7):1703\u20131719. https:\/\/doi.org\/10.1038\/s41375-022-01613-1","journal-title":"Leukemia"},{"issue":"1","key":"7257_CR4","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1111\/bjh.70231","volume":"208","author":"JN Eckardt","year":"2026","unstructured":"Eckardt JN, Walter W, Middeke JM, Haferlach T (2026) Artificial intelligence for risk assessment and outcome prediction in malignant haematology. Br J Haematol 208(1):25\u201338. https:\/\/doi.org\/10.1111\/bjh.70231","journal-title":"Br J Haematol"},{"key":"7257_CR5","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1186\/s12859-024-05758-x","volume":"25","author":"JM Dolezal","year":"2024","unstructured":"Dolezal JM, Kochanny S, Dyer E et al (2024) Slideflow: deep learning for digital histopathology with real-time whole-slide visualization. BMC Bioinformatics 25:134. https:\/\/doi.org\/10.1186\/s12859-024-05758-x","journal-title":"BMC Bioinformatics"},{"issue":"10","key":"7257_CR6","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","volume":"30","author":"E Vorontsov","year":"2024","unstructured":"Vorontsov E, Bozkurt A, Casson A et al (2024) A foundation model for clinical-grade computational pathology and rare cancers detection. Nat Med 30(10):2924\u20132935. https:\/\/doi.org\/10.1038\/s41591-024-03141-0","journal-title":"Nat Med"},{"key":"7257_CR7","doi-asserted-by":"publisher","unstructured":"Kingma DP, Ba J, Adam A Method for Stochastic Optimization. arXiv. Preprint posted online 30 January 2017:arXiv:1412.6980. https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"7257_CR8","doi-asserted-by":"publisher","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M, Optuna (2019) A Next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. KDD \u201919. Association for computing machinery, 2623\u20132631. https:\/\/doi.org\/10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"issue":"1","key":"7257_CR9","doi-asserted-by":"publisher","first-page":"3367","DOI":"10.1038\/s41598-021-82826-9","volume":"11","author":"K Kimura","year":"2021","unstructured":"Kimura K, Ai T, Horiuchi Y et al (2021) Automated diagnostic support system with deep learning algorithms for distinction of Philadelphia chromosome-negative myeloproliferative neoplasms using peripheral blood specimen. Sci Rep 11(1):3367. https:\/\/doi.org\/10.1038\/s41598-021-82826-9","journal-title":"Sci Rep"},{"issue":"11","key":"7257_CR10","doi-asserted-by":"publisher","first-page":"2691","DOI":"10.3324\/haematol.2024.286123","volume":"110","author":"D Yu","year":"2025","unstructured":"Yu D, Zhang H, Song Y et al (2025) Artificial intelligence-based quantitative bone marrow pathology analysis for myeloproliferative neoplasms. Haematologica 110(11):2691\u20132701. https:\/\/doi.org\/10.3324\/haematol.2024.286123","journal-title":"Haematologica"},{"issue":"2","key":"7257_CR11","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1111\/bjh.19938","volume":"206","author":"R Wang","year":"2025","unstructured":"Wang R, Shi Z, Zhang Y et al (2025) Development and validation of a deep learning model for morphological assessment of myeloproliferative neoplasms using clinical data and digital pathology. Br J Haematol 206(2):596\u2013606. https:\/\/doi.org\/10.1111\/bjh.19938","journal-title":"Br J Haematol"},{"issue":"14","key":"7257_CR12","doi-asserted-by":"publisher","first-page":"3284","DOI":"10.1182\/bloodadvances.2020002230","volume":"4","author":"K Sirinukunwattana","year":"2020","unstructured":"Sirinukunwattana K, Aberdeen A, Theissen H et al (2020) Artificial intelligence\u2013based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients. Blood Adv 4(14):3284\u20133294. https:\/\/doi.org\/10.1182\/bloodadvances.2020002230","journal-title":"Blood Adv"},{"issue":"2","key":"7257_CR13","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1038\/s41375-022-01773-0","volume":"37","author":"H Ryou","year":"2023","unstructured":"Ryou H, Sirinukunwattana K, Aberdeen A et al (2023) Continuous Indexing of Fibrosis (CIF): improving the assessment and classification of MPN patients. Leukemia 37(2):348\u2013358. https:\/\/doi.org\/10.1038\/s41375-022-01773-0","journal-title":"Leukemia"},{"key":"7257_CR14","doi-asserted-by":"publisher","first-page":"3600","DOI":"10.1182\/blood-2024-208380","volume":"144","author":"S Krichevsky","year":"2024","unstructured":"Krichevsky S, Zhang Y, Ouseph MM et al (2024) Deep Learning Predicts JAK2, Calr TET2, and ASXL1 directly from Whole Slide Marrow Images. Blood 144:3600. https:\/\/doi.org\/10.1182\/blood-2024-208380","journal-title":"Blood"}],"container-title":["Annals of Hematology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00277-026-07257-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00277-026-07257-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00277-026-07257-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:42:52Z","timestamp":1789465372000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00277-026-07257-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":14,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["7257"],"URL":"https:\/\/doi.org\/10.1007\/s00277-026-07257-w","relation":{},"ISSN":["1432-0584"],"issn-type":[{"value":"1432-0584","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"3 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"JNE, SR, TS, MB, and JMM are part-owners of Cancilico. MT is part owner of Institute for Hematopathology Hamburg. The other authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"393"}}