{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T05:39:35Z","timestamp":1790746775843,"version":"4.1.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009448","name":"Universit\u00e0 degli Studi della Campania Luigi Vanvitelli","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009448","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Virchows Arch"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Bone marrow fibrosis plays a critical role in the diagnosis, prognosis, and management of haematological disorders, particularly myeloproliferative neoplasms like primary myelofibrosis. Accurate assessment of fibrosis, typically graded through histochemical techniques such as reticulin and trichrome staining, is essential but remains highly dependent on the pathologist\u2019s experience. To address the challenges of variability in interpretation and the increasing demand for standardized evaluations, we developed a digital pathology system for automated bone marrow reticulin fibrosis grading. This study utilized 86 bone marrow biopsy specimens from patients diagnosed with Philadelphia chromosome-negative myeloproliferative neoplasms, collected between 2018 and 2023. A fully convolutional network based on the InceptionV3 architecture was trained to assess fibrosis grades (MF0\u2013MF3) from whole slide images of reticulin-stained sections. The model was trained using 3814 annotated images and validated using a separate set of 40 BMBs. The algorithm\u2019s performance was evaluated by comparing its fibrosis grading to expert hematopathologists\u2019 assessments, yielding a Cohen\u2019s kappa coefficient of 0.831, indicating excellent agreement. The algorithm showed strong concordance in fibrosis grading, especially for MF0 (\n                    <jats:italic>k<\/jats:italic>\n                    \u2009=\u20090.918) and MF3 (\n                    <jats:italic>k<\/jats:italic>\n                    \u2009=\u20090.886), and substantial agreement for intermediate grades (MF1 and MF2). Further validation across multiple institutions and scanning platforms confirmed the algorithm\u2019s robustness, with an overall agreement of 0.816. These results demonstrate the potential of digital pathology tools to provide standardized, reproducible fibrosis grading, thereby aiding pathologists in clinical decision-making and training.\n                  <\/jats:p>","DOI":"10.1007\/s00428-025-04122-5","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T09:05:00Z","timestamp":1747127100000},"page":"495-502","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Development of an automated artificial intelligence-based tool for reticulin fibrosis assessment in bone marrow biopsies"],"prefix":"10.1007","volume":"489","author":[{"given":"Giuseppe","family":"D\u2019Abbronzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"D\u2019Antonio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annarosaria","family":"De Chiara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Panico","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucianna","family":"Sparano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Diluvio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonello","family":"Sica","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gino","family":"Svanera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"De Chiara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mariano","family":"Fuggi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ferdinando","family":"Russo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8340-3184","authenticated-orcid":false,"given":"Renato","family":"Franco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Ronchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"4122_CR1","unstructured":"WHO Classification of Tumours Editorial Board (2024) Haematolymphoid tumours 5th edn. International agency for research on cancer, Lyon"},{"key":"4122_CR2","doi-asserted-by":"publisher","first-page":"660","DOI":"10.3324\/haematol.2015.141283","volume":"101","author":"AA Zahr","year":"2016","unstructured":"Zahr AA, Salama ME, Carreau N et al (2016) Bone marrow fibrosis in myelofibrosis: pathogenesis, prognosis and targeted strategies. Haematologica 101:660\u2013671. https:\/\/doi.org\/10.3324\/haematol.2015.141283","journal-title":"Haematologica"},{"key":"4122_CR3","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1186\/s12967-023-04393-z","volume":"21","author":"K Ghosh","year":"2023","unstructured":"Ghosh K, Shome DK, Kulkarni B et al (2023) Fibrosis and bone marrow: understanding causation and pathobiology. J Transl Med 21:703. https:\/\/doi.org\/10.1186\/s12967-023-04393-z","journal-title":"J Transl Med"},{"key":"4122_CR4","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1038\/modpathol.2012.87","volume":"25","author":"U Gianelli","year":"2012","unstructured":"Gianelli U, Vener C, Bossi A et al (2012) The European Consensus on grading of bone marrow fibrosis allows a better prognostication of patients with primary myelofibrosis. Mod Pathol 25:1193\u20131202. https:\/\/doi.org\/10.1038\/modpathol.2012.87","journal-title":"Mod Pathol"},{"key":"4122_CR5","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.11406\/rinketsu.60.1166","volume":"60","author":"HM Kvasnicka","year":"2019","unstructured":"Kvasnicka HM (2019) The differential diagnosis of classical myeloproliferative neoplasms (MPN): the updated WHO criteria. Rinsho Ketsueki 60:1166\u20131175. https:\/\/doi.org\/10.11406\/rinketsu.60.1166","journal-title":"Rinsho Ketsueki"},{"key":"4122_CR6","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.3390\/jcm12062188","volume":"12","author":"A Duminuco","year":"2023","unstructured":"Duminuco A, Nardo A, Giuffrida G et al (2023) Myelofibrosis and survival prognostic models: a journey between past and future. J Clin Med 12:2188. https:\/\/doi.org\/10.3390\/jcm12062188","journal-title":"J Clin Med"},{"key":"4122_CR7","doi-asserted-by":"publisher","first-page":"101128","DOI":"10.1016\/j.blre.2023.101128","volume":"62","author":"M Stahl","year":"2023","unstructured":"Stahl M, Bewersdorf JP, Xie Z et al (2023) Classification, risk stratification and response assessment in myelodysplastic syndromes\/neoplasms (MDS): a state-of-the-art report on behalf of the International Consortium for MDS (icMDS). Blood Rev 62:101128. https:\/\/doi.org\/10.1016\/j.blre.2023.101128","journal-title":"Blood Rev"},{"key":"4122_CR8","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1038\/bmt.2014.323","volume":"50","author":"R Tamari","year":"2015","unstructured":"Tamari R, Mughal TI, Rondelli D et al (2015) Allo-SCT for myelofibrosis: reversing the chronic phase in the JAK inhibitor era? Bone Marrow Transplant 50:628\u2013636. https:\/\/doi.org\/10.1038\/bmt.2014.323","journal-title":"Bone Marrow Transplant"},{"key":"4122_CR9","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1182\/blood-2007-09-112953","volume":"111","author":"C Vener","year":"2008","unstructured":"Vener C, Fracchiolla NS, Gianelli U et al (2008) Prognostic implications of the European consensus for grading of bone marrow fibrosis in chronic idiopathic myelofibrosis. Blood 111:1862\u20131865. https:\/\/doi.org\/10.1182\/blood-2007-09-112953","journal-title":"Blood"},{"key":"4122_CR10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1182\/blood-2007-05-091850","volume":"111","author":"BS Wilkins","year":"2008","unstructured":"Wilkins BS, Erber WN, Bareford D et al (2008) Bone marrow pathology in essential thrombocythemia: interobserver reliability and utility for identifying disease subtypes. Blood 111:60\u201370. https:\/\/doi.org\/10.1182\/blood-2007-05-091850","journal-title":"Blood"},{"key":"4122_CR11","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1038\/modpathol.2013.196","volume":"27","author":"U Gianelli","year":"2014","unstructured":"Gianelli U, Bossi A, Cortinovis I et al (2014) Reproducibility of the WHO histological criteria for the diagnosis of Philadelphia chromosome-negative myeloproliferative neoplasms. Mod Pathol 27:814\u2013822. https:\/\/doi.org\/10.1038\/modpathol.2013.196","journal-title":"Mod Pathol"},{"key":"4122_CR12","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1093\/ajcp\/56.1.24","volume":"56","author":"DE Bauermeister","year":"1971","unstructured":"Bauermeister DE (1971) Quantitation of bone marrow reticulin\u2014a normal range. Am J Clin Pathol 56:24\u201331. https:\/\/doi.org\/10.1093\/ajcp\/56.1.24","journal-title":"Am J Clin Pathol"},{"key":"4122_CR13","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1038\/modpathol.2014.69","volume":"27","author":"O Pozdnyakova","year":"2014","unstructured":"Pozdnyakova O, Wu K, Patki A et al (2014) High concordance in grading reticulin fibrosis and cellularity in patients with myeloproliferative neoplasms. Mod Pathol 27:1447\u20131454. https:\/\/doi.org\/10.1038\/modpathol.2014.69","journal-title":"Mod Pathol"},{"key":"4122_CR14","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1111\/his.12871","volume":"68","author":"HM Kvasnicka","year":"2016","unstructured":"Kvasnicka HM, Beham-Schmid C, Bob R et al (2016) Problems and pitfalls in grading of bone marrow fibrosis, collagen deposition and osteosclerosis \u2013 a consensus-based study. Histopathology 68:905\u2013915. https:\/\/doi.org\/10.1111\/his.12871","journal-title":"Histopathology"},{"key":"4122_CR15","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s13000-023-01375-z","volume":"18","author":"S Shafi","year":"2023","unstructured":"Shafi S, Parwani AV (2023) Artificial intelligence in diagnostic pathology. Diagn Pathol 18:109. https:\/\/doi.org\/10.1186\/s13000-023-01375-z","journal-title":"Diagn Pathol"},{"key":"4122_CR16","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.3390\/cancers16091687","volume":"16","author":"G D\u2019Abbronzo","year":"2024","unstructured":"D\u2019Abbronzo G, D\u2019Antonio A, De Chiara A et al (2024) Development of an artificial-intelligence-based tool for automated assessment of cellularity in bone marrow biopsies in Ph-negative myeloproliferative neoplasms. Cancers (Basel) 16:1687. https:\/\/doi.org\/10.3390\/cancers16091687","journal-title":"Cancers (Basel)"},{"key":"4122_CR17","doi-asserted-by":"publisher","first-page":"16878","DOI":"10.1038\/s41598-017-17204-5","volume":"7","author":"P Bankhead","year":"2017","unstructured":"Bankhead P, Loughrey MB, Fern\u00e1ndez JA et al (2017) QuPath: open source software for digital pathology image analysis. Sci Rep 7:16878. https:\/\/doi.org\/10.1038\/s41598-017-17204-5","journal-title":"Sci Rep"},{"key":"4122_CR18","doi-asserted-by":"publisher","unstructured":"Pettersen HS, Belevich I, R\u00f8yset ES, et al (2022) Code-free development and deployment of deep segmentation models for digital pathology. Front Med (Lausanne) 8. https:\/\/doi.org\/10.3389\/fmed.2021.816281","DOI":"10.3389\/fmed.2021.816281"},{"key":"4122_CR19","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 (2015) FAST: framework for heterogeneous medical image computing and visualization. Int J Comput Assist Radiol Surg 10:1811\u20131822. https:\/\/doi.org\/10.1007\/s11548-015-1158-5","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"4122_CR20","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med (Zagreb) 22:276\u2013282","journal-title":"Biochem Med (Zagreb)"},{"key":"4122_CR21","doi-asserted-by":"publisher","first-page":"172","DOI":"10.32074\/1591-951X-852","volume":"115","author":"G D\u2019Abbronzo","year":"2023","unstructured":"D\u2019Abbronzo G, Luc\u00e0 S, Carraturo E et al (2023) Shortage of pathologists in Italy: survey of students and residents. Pathologica 115:172\u2013180. https:\/\/doi.org\/10.32074\/1591-951X-852","journal-title":"Pathologica"},{"key":"4122_CR22","doi-asserted-by":"publisher","first-page":"e194337","DOI":"10.1001\/jamanetworkopen.2019.4337","volume":"2","author":"DM Metter","year":"2019","unstructured":"Metter DM, Colgan TJ, Leung ST et al (2019) Trends in the US and Canadian pathologist workforces from 2007 to 2017. JAMA Netw Open 2:e194337. https:\/\/doi.org\/10.1001\/jamanetworkopen.2019.4337","journal-title":"JAMA Netw Open"},{"key":"4122_CR23","doi-asserted-by":"publisher","unstructured":"Gu H, Huang J, Hung L, Chen X \u201cAnthony\u201d (2021) Lessons learned from designing an AI-enabled diagnosis tool for pathologists. Proc ACM Hum Comput Interact 5:1\u201325. https:\/\/doi.org\/10.1145\/3449084","DOI":"10.1145\/3449084"},{"key":"4122_CR24","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1038\/s41698-020-0120-3","volume":"4","author":"M Chen","year":"2020","unstructured":"Chen M, Zhang B, Topatana W et al (2020) Classification and mutation prediction based on histopathology H&E images in liver cancer using deep learning. NPJ Precis Oncol 4:14. https:\/\/doi.org\/10.1038\/s41698-020-0120-3","journal-title":"NPJ Precis Oncol"},{"key":"4122_CR25","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 37:348\u2013358. https:\/\/doi.org\/10.1038\/s41375-022-01773-0","journal-title":"Leukemia"},{"key":"4122_CR26","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1016\/j.leukres.2010.01.005","volume":"34","author":"CJ Teman","year":"2010","unstructured":"Teman CJ, Wilson AR, Perkins SL et al (2010) Quantification of fibrosis and osteosclerosis in myeloproliferative neoplasms: a computer-assisted image study. Leuk Res 34:871\u2013876. https:\/\/doi.org\/10.1016\/j.leukres.2010.01.005","journal-title":"Leuk Res"},{"key":"4122_CR27","doi-asserted-by":"publisher","first-page":"100321","DOI":"10.1016\/j.jpi.2023.100321","volume":"14","author":"SR Duenweg","year":"2023","unstructured":"Duenweg SR, Bobholz SA, Lowman AK et al (2023) Whole slide imaging (WSI) scanner differences influence optical and computed properties of digitized prostate cancer histology. J Pathol Inform 14:100321. https:\/\/doi.org\/10.1016\/j.jpi.2023.100321","journal-title":"J Pathol Inform"},{"key":"4122_CR28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.4103\/2153-3539.197205","volume":"7","author":"P Shrestha","year":"2016","unstructured":"Shrestha P, Kneepkens R, Vrijnsen J et al (2016) A quantitative approach to evaluate image quality of whole slide imaging scanners. J Pathol Inform 7:56. https:\/\/doi.org\/10.4103\/2153-3539.197205","journal-title":"J Pathol Inform"}],"container-title":["Virchows Archiv"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-025-04122-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00428-025-04122-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-025-04122-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T09:25:10Z","timestamp":1786785910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00428-025-04122-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,13]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["4122"],"URL":"https:\/\/doi.org\/10.1007\/s00428-025-04122-5","relation":{},"ISSN":["0945-6317","1432-2307"],"issn-type":[{"value":"0945-6317","type":"print"},{"value":"1432-2307","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,13]]},"assertion":[{"value":"6 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was conducted in accordance with the Declaration of Helsinki and with the approval of the Internal Review Board of the I.N.T. Pascale (Approval Code: CEI 556\/10. Approval Date: 12 March 2010).Images for the training and test sets are anonymous; however, informed consent for the use of biological material for scientific purposes was preliminarily obtained from the patients.","order":1,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}