{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T03:40:07Z","timestamp":1792813207443,"version":"4.5.0"},"reference-count":34,"publisher":"American Society of Hematology","issue":"14","content-domain":{"domain":["ashpublications.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate diagnosis and classification of myeloproliferative neoplasms (MPNs) requires integration of clinical, morphological, and genetic findings. Despite major advances in our understanding of the molecular and genetic basis of MPNs, the morphological assessment of bone marrow trephines (BMT) is critical in differentiating MPN subtypes and their reactive mimics. However, morphological assessment is heavily constrained by a reliance on subjective, qualitative, and poorly reproducible criteria. To improve the morphological assessment of MPNs, we have developed a machine learning approach for the automated identification, quantitative analysis, and abstract representation of megakaryocyte features using reactive\/nonneoplastic BMT samples (n = 43) and those from patients with established diagnoses of essential thrombocythemia (n = 45), polycythemia vera (n = 18), or myelofibrosis (n = 25). We describe the application of an automated workflow for the identification and delineation of relevant histological features from routinely prepared BMTs. Subsequent analysis enabled the tissue diagnosis of MPN with a high predictive accuracy (area under the curve = 0.95) and revealed clear evidence of the potential to discriminate between important MPN subtypes. Our method of visually representing abstracted megakaryocyte features in the context of analyzed patient cohorts facilitates the interpretation and monitoring of samples in a manner that is beyond conventional approaches. The automated BMT phenotyping approach described here has significant potential as an adjunct to standard genetic and molecular testing in established or suspected MPN patients, either as part of the routine diagnostic pathway or in the assessment of disease progression\/response to treatment.<\/jats:p>","DOI":"10.1182\/bloodadvances.2020002230","type":"journal-article","created":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T11:38:22Z","timestamp":1595590702000},"page":"3284-3294","update-policy":"https:\/\/doi.org\/10.1182\/blood.2019cm0000","source":"Crossref","is-referenced-by-count":88,"title":["Artificial intelligence\u2013based morphological fingerprinting of megakaryocytes: a new tool for assessing disease in MPN patients"],"prefix":"10.1182","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3603-4435","authenticated-orcid":false,"given":"Korsuk","family":"Sirinukunwattana","sequence":"first","affiliation":[{"name":"Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, United Kingdom;"},{"name":"Ground Truth Labs, Oxford, United Kingdom;"},{"name":"Big Data Institute\/Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford, United Kingdom;"},{"name":"NIHR Oxford Biomedical Research Centre, Oxford University NHS Foundation Trust, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5483-0905","authenticated-orcid":false,"given":"Alan","family":"Aberdeen","sequence":"additional","affiliation":[{"name":"Ground Truth Labs, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4628-9722","authenticated-orcid":false,"given":"Helen","family":"Theissen","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, United Kingdom;"},{"name":"Big Data Institute\/Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9100-2954","authenticated-orcid":false,"given":"Nikolaos","family":"Sousos","sequence":"additional","affiliation":[{"name":"Medical Research Council (MRC) Molecular Haematology Unit, MRC Weatherall Institute of Molecular Medicine, and"},{"name":"Haematopoietic Stem Cell Biology Laboratory, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8198-9663","authenticated-orcid":false,"given":"Bethan","family":"Psaila","sequence":"additional","affiliation":[{"name":"NIHR Oxford Biomedical Research Centre, Oxford University NHS Foundation Trust, Oxford, United Kingdom;"},{"name":"Medical Research Council (MRC) Molecular Haematology Unit, MRC Weatherall Institute of Molecular Medicine, and"},{"name":"Haematopoietic Stem Cell Biology Laboratory, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8522-1002","authenticated-orcid":false,"given":"Adam J.","family":"Mead","sequence":"additional","affiliation":[{"name":"NIHR Oxford Biomedical Research Centre, Oxford University NHS Foundation Trust, Oxford, United Kingdom;"},{"name":"Medical Research Council (MRC) Molecular Haematology Unit, MRC Weatherall Institute of Molecular Medicine, and"},{"name":"Haematopoietic Stem Cell Biology Laboratory, MRC Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, United Kingdom;"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gareth D. H.","family":"Turner","sequence":"additional","affiliation":[{"name":"Department of Cellular Pathology, John Radcliffe Hospital, Oxford University NHS Foundation Trust, Oxford, United Kingdom; and"},{"name":"Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, John Radcliffe Hospital, and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabrielle","family":"Rees","sequence":"additional","affiliation":[{"name":"Department of Cellular Pathology, John Radcliffe Hospital, Oxford University NHS Foundation Trust, Oxford, United Kingdom; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8528-8298","authenticated-orcid":false,"given":"Jens","family":"Rittscher","sequence":"additional","affiliation":[{"name":"Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, United Kingdom;"},{"name":"Ground Truth Labs, Oxford, United Kingdom;"},{"name":"Big Data Institute\/Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford, United Kingdom;"},{"name":"NIHR Oxford Biomedical Research Centre, Oxford University NHS Foundation Trust, Oxford, United Kingdom;"},{"name":"Ludwig Institute for Cancer Research\/Nuffield Department of Medicine, University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5151-2378","authenticated-orcid":false,"given":"Daniel","family":"Royston","sequence":"additional","affiliation":[{"name":"Department of Cellular Pathology, John Radcliffe Hospital, Oxford University NHS Foundation Trust, Oxford, United Kingdom; and"},{"name":"Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, John Radcliffe Hospital, and"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"234","published-online":{"date-parts":[[2020,7,24]]},"reference":[{"issue":"22","key":"2020072411361628500_B1","doi-asserted-by":"crossref","first-page":"e123","DOI":"10.1182\/blood-2014-02-554634","article-title":"Integrated genomic analysis illustrates the central role of JAK-STAT pathway activation in myeloproliferative neoplasm pathogenesis","volume":"123","author":"Rampal","year":"2014","journal-title":"Blood"},{"key":"2020072411361628500_B2","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.jbior.2018.11.007","article-title":"Heterogeneity in myeloproliferative neoplasms: causes and consequences","volume":"71","author":"O\u2019Sullivan","year":"2019","journal-title":"Adv Biol Regul"},{"issue":"7","key":"2020072411361628500_B3","doi-asserted-by":"crossref","first-page":"1660","DOI":"10.1038\/leu.2017.119","article-title":"Equivalence of BCSH and WHO diagnostic criteria for ET","volume":"31","author":"Harrison","year":"2017","journal-title":"Leukemia"},{"issue":"2","key":"2020072411361628500_B4","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/s41408-018-0054-y","article-title":"The 2016 WHO classification and diagnostic criteria for myeloproliferative neoplasms: document summary and in-depth discussion","volume":"8","author":"Barbui","year":"2018","journal-title":"Blood Cancer J"},{"issue":"3","key":"2020072411361628500_B5","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1182\/blood-2015-07-661983","article-title":"Presence of atypical thrombopoietin receptor (MPL) mutations in triple-negative essential thrombocythemia patients","volume":"127","author":"Cabagnols","year":"2016","journal-title":"Blood"},{"issue":"7","key":"2020072411361628500_B6","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1182\/blood-2014-05-578435","article-title":"Clinical effect of driver mutations of JAK2, CALR, or MPL in primary myelofibrosis","volume":"124","author":"Rumi","year":"2014","journal-title":"Blood"},{"issue":"24","key":"2020072411361628500_B7","doi-asserted-by":"crossref","first-page":"3714","DOI":"10.1182\/blood-2014-03-530865","article-title":"From Janus kinase 2 to calreticulin: the clinically relevant genomic landscape of myeloproliferative neoplasms","volume":"123","author":"Cazzola","year":"2014","journal-title":"Blood"},{"issue":"20","key":"2020072411361628500_B8","doi-asserted-by":"crossref","first-page":"2391","DOI":"10.1182\/blood-2016-03-643544","article-title":"The 2016 revision to the World Health Organization classification of myeloid neoplasms and acute leukemia","volume":"127","author":"Arber","year":"2016","journal-title":"Blood"},{"key":"2020072411361628500_B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4103\/2153-3539.63821","article-title":"Digital images and the future of digital pathology","volume":"1","author":"Pantanowitz","year":"2010","journal-title":"J Pathol Inform"},{"issue":"1","key":"2020072411361628500_B10","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1146\/annurev-bioeng-112415-114722","article-title":"Emerging Themes in Image Informatics and Molecular Analysis for Digital Pathology","volume":"18","author":"Bhargava","year":"2016","journal-title":"Annu Rev Biomed Eng"},{"key":"2020072411361628500_B11","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.ebiom.2017.12.026","article-title":"Deep convolutional neural networks enable discrimination of heterogeneous digital pathology images","volume":"27","author":"Khosravi","year":"2018","journal-title":"EBioMedicine"},{"issue":"1","key":"2020072411361628500_B12","doi-asserted-by":"crossref","first-page":"46450","DOI":"10.1038\/srep46450","article-title":"Accurate and reproducible invasive breast cancer detection in whole-slide images: a deep learning approach for quantifying tumor extent","volume":"7","author":"Cruz-Roa","year":"2017","journal-title":"Sci Rep"},{"key":"2020072411361628500_B13","first-page":"1899","article-title":"Automated grading of gliomas using deep learning in digital pathology images: a modular approach with ensemble of convolutional neural networks","volume":"2015","author":"Ertosun","year":"2015","journal-title":"AMIA Annu Symp Proc"},{"issue":"5","key":"2020072411361628500_B14","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TMI.2016.2525803","article-title":"Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images","volume":"35","author":"Sirinukunwattana","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"issue":"28","key":"2020072411361628500_B15","doi-asserted-by":"crossref","first-page":"44381","DOI":"10.18632\/oncotarget.10053","article-title":"Novel histopathologic feature identified through image analysis augments stage II colorectal cancer clinical reporting","volume":"7","author":"Caie","year":"2016","journal-title":"Oncotarget"},{"issue":"1","key":"2020072411361628500_B16","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1186\/1479-5876-12-156","article-title":"Quantification of tumour budding, lymphatic vessel density and invasion through image analysis in colorectal cancer","volume":"12","author":"Caie","year":"2014","journal-title":"J Transl Med"},{"issue":"1","key":"2020072411361628500_B17","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1038\/s41598-018-37257-4","article-title":"Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard","volume":"9","author":"Bulten","year":"2019","journal-title":"Sci Rep"},{"issue":"9","key":"2020072411361628500_B18","first-page":"895","article-title":"Myeloproliferative Neoplasms","volume":"377","author":"Spivak","year":"2017","journal-title":"N Engl J Med"},{"issue":"1","key":"2020072411361628500_B19","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1182\/blood-2007-05-091850","article-title":"Bone marrow pathology in essential thrombocythemia: interobserver reliability and utility for identifying disease subtypes","volume":"111","author":"Wilkins","year":"2008","journal-title":"Blood"},{"issue":"6","key":"2020072411361628500_B20","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1111\/bjh.12990","article-title":"WHO-histological criteria for myeloproliferative neoplasms: reproducibility, diagnostic accuracy and correlation with gene mutations and clinical outcomes","volume":"166","author":"Alvarez-Larr\u00e1n","year":"2014","journal-title":"Br J Haematol"},{"issue":"3","key":"2020072411361628500_B21","doi-asserted-by":"crossref","first-page":"360","DOI":"10.3324\/haematol.2011.047811","article-title":"European Bone Marrow Working Group trial on reproducibility of World Health Organization criteria to discriminate essential thrombocythemia from prefibrotic primary myelofibrosis","volume":"97","author":"Buhr","year":"2012","journal-title":"Haematologica"},{"issue":"9","key":"2020072411361628500_B22","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1111\/apm.12417","article-title":"WHO classification 2008 of myeloproliferative neoplasms: a workshop learning effect\u2014the Danish experience","volume":"123","author":"Madelung","year":"2015","journal-title":"APMIS"},{"key":"2020072411361628500_B23","doi-asserted-by":"crossref","unstructured":"Huang\n              J\n            , RathodV, SunC, et al. Speed\/accuracy trade-offs for modern convolutional object detectors. arXiv. 2017; arXiv:1611.10012.","DOI":"10.1109\/CVPR.2017.351"},{"key":"2020072411361628500_B24","author":"Liu"},{"issue":"1","key":"2020072411361628500_B25","doi-asserted-by":"crossref","first-page":"26286","DOI":"10.1038\/srep26286","article-title":"Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis","volume":"6","author":"Litjens","year":"2016","journal-title":"Sci Rep"},{"key":"2020072411361628500_B26","author":"Ronneberger"},{"issue":"9","key":"2020072411361628500_B27","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","volume":"78","author":"Kohonen","year":"1990","journal-title":"Proc IEEE"},{"issue":"7","key":"2020072411361628500_B28","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1093\/nar\/30.7.1575","article-title":"An efficient algorithm for large-scale detection of protein families","volume":"30","author":"Enright","year":"2002","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"2020072411361628500_B29","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1159\/000493970","article-title":"JAK2V617F, CALR, and MPL mutations and bone marrow histology in patients with essential thrombocythaemia","volume":"140","author":"Pich","year":"2018","journal-title":"Acta Haematol"},{"key":"2020072411361628500_B30","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1097\/01.HS9.0000567380.33673.ae","article-title":"PB2225 Artificial intelligence aiding in diagnosis of JAK2 V617F negative patients with WHO defined essential thrombocythemia","volume":"3","author":"Belcic","year":"2019","journal-title":"HemaSphere"},{"issue":"6","key":"2020072411361628500_B31","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1111\/ijlh.13089","article-title":"Machine learning applications in the diagnosis of leukemia: Current trends and future directions","volume":"41","author":"Salah","year":"2019","journal-title":"Int J Lab Hematol"},{"issue":"4","key":"2020072411361628500_B32","doi-asserted-by":"crossref","first-page":"e15963","DOI":"10.2196\/15963","article-title":"A hematologist-level deep learning algorithm (BMSNet) for assessing the morphologies of single nuclear balls in bone marrow smears: algorithm development","volume":"8","author":"Wu","year":"2020","journal-title":"JMIR Med Inform"},{"issue":"6","key":"2020072411361628500_B33","doi-asserted-by":"crossref","first-page":"e0218808","DOI":"10.1371\/journal.pone.0218808","article-title":"Deep learning approach to peripheral leukocyte recognition","volume":"14","author":"Wang","year":"2019","journal-title":"PLoS One"},{"issue":"1","key":"2020072411361628500_B34","doi-asserted-by":"crossref","first-page":"13385","DOI":"10.1038\/s41598-019-49942-z","article-title":"A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA","volume":"9","author":"Kimura","year":"2019","journal-title":"Sci Rep"}],"container-title":["Blood Advances"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/ashpublications.org\/bloodadvances\/article-pdf\/4\/14\/3284\/1749738\/advancesadv2020002230.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/ashpublications.org\/bloodadvances\/article-pdf\/4\/14\/3284\/1749738\/advancesadv2020002230.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T11:38:59Z","timestamp":1595590739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ashpublications.org\/bloodadvances\/article\/4\/14\/3284\/461548\/Artificial-intelligencebased-morphological"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,24]]},"references-count":34,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2020,7,28]]}},"URL":"https:\/\/doi.org\/10.1182\/bloodadvances.2020002230","relation":{},"ISSN":["2473-9529","2473-9537"],"issn-type":[{"value":"2473-9529","type":"print"},{"value":"2473-9537","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,24]]}}}