{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:45:48Z","timestamp":1792788348135,"version":"4.5.0"},"reference-count":12,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e4tsklinikum W\u00fcrzburg","id":[{"id":"https:\/\/ror.org\/03pvr2g57","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Res Notes"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and empirically characterize a domain-specific, block-structured annotation schema and an expert-annotated reference corpus for German-language head and neck squamous cell carcinoma (HNSCC) pathology reports.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results description<\/jats:title>\n                    <jats:p>We retrieved 631 pathology reports from 145 patients treated at University Hospital W\u00fcrzburg between January 2021 and March 2024 and split them at the patient level into training, validation, and evaluation subsets. Reports were manually annotated using a hierarchical, span-based schema supporting overlapping and nested annotations. The resulting corpus contains 45 unique labels organized into clinically meaningful blocks and an average of 37\u201339 annotations per report across subsets. Label frequencies and normalized category distributions were broadly comparable across the three subsets. Fine-grained labels were predominantly applied within their designated blocks, indicating adherence to the intended block structure. The corpus provides a domain-specific reference resource for developing and evaluating structured information-extraction approaches for German HNSCC pathology reports.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13104-026-08024-w","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:04:40Z","timestamp":1789992280000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A domain-specific annotation framework and expert-annotated corpus for structured analysis of German HNSCC pathology reports"],"prefix":"10.1186","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7312-5519","authenticated-orcid":false,"given":"Sebastian","family":"Gubik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franziska","family":"Seger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Vollmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"H\u00f6rner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Renner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Kohlhepp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Manthey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Urs","family":"M\u00fcller-Richter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"K\u00fcbler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Hackenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Hartmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"8024_CR1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","volume":"68","author":"F Bray","year":"2018","unstructured":"Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68:394\u2013424. https:\/\/doi.org\/10.3322\/caac.21492.","journal-title":"CA Cancer J Clin"},{"key":"8024_CR2","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1056\/NEJMra1715715","volume":"382","author":"LQM Chow","year":"2020","unstructured":"Chow LQM. Head and neck cancer. N Engl J Med. 2020;382:60\u201372. https:\/\/doi.org\/10.1056\/NEJMra1715715.","journal-title":"N Engl J Med"},{"key":"8024_CR3","doi-asserted-by":"publisher","first-page":"3235","DOI":"10.1200\/JCO.2015.61.6995","volume":"33","author":"ML Gillison","year":"2015","unstructured":"Gillison ML, Chaturvedi AK, Anderson WF, Fakhry C. Epidemiology of human papillomavirus\u2013positive head and neck squamous cell carcinoma. J Clin Oncol. 2015;33:3235\u201342. https:\/\/doi.org\/10.1200\/JCO.2015.61.6995.","journal-title":"J Clin Oncol"},{"key":"8024_CR4","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1056\/NEJMoa1602252","volume":"375","author":"RL Ferris","year":"2016","unstructured":"Ferris RL, Blumenschein G Jr, Fayette J, Guigay J, Colevas AD, Licitra L, et al. Nivolumab for recurrent squamous-cell carcinoma of the head and neck. N Engl J Med. 2016;375:1856\u201367. https:\/\/doi.org\/10.1056\/NEJMoa1602252.","journal-title":"N Engl J Med"},{"key":"8024_CR5","doi-asserted-by":"publisher","first-page":"e22","DOI":"10.3414\/ME17-02-0010","volume":"57","author":"G Dietrich","year":"2018","unstructured":"Dietrich G, Lohmeyer Q, Sch\u00e4fer T, Hinderer M, Fette G, St\u00e4ubert S, et al. Ad hoc information extraction for clinical data warehouses. Methods Inf Med. 2018;57:e22\u20139. https:\/\/doi.org\/10.3414\/ME17-02-0010.","journal-title":"Methods Inf Med"},{"issue":"7","key":"8024_CR6","doi-asserted-by":"publisher","first-page":"999","DOI":"10.3390\/jcm8070999","volume":"8","author":"S Loda","year":"2019","unstructured":"Loda S, Simonyan V, Mendes M, Miller R, Stewart M, Kline D, et al. Exploration of artificial intelligence use with ARIES in multiple myeloma research. J Clin Med. 2019;8(7):999. https:\/\/doi.org\/10.3390\/jcm8070999.","journal-title":"J Clin Med"},{"key":"8024_CR7","doi-asserted-by":"publisher","DOI":"10.1136\/jcp-2024-209669","author":"R Geevarghese","year":"2024","unstructured":"Geevarghese R, et al. Extraction and classification of structured data from unstructured hepatobiliary pathology reports using large language models: a feasibility study compared with rules-based natural language processing. J Clin Pathol. 2024. https:\/\/doi.org\/10.1136\/jcp-2024-209669.","journal-title":"J Clin Pathol"},{"key":"8024_CR8","doi-asserted-by":"crossref","unstructured":"Borchert F et al. GGPONC: a corpus of German medical text with rich metadata based on clinical practice guidelines. arXiv preprint arXiv:2007.06400. 2020.","DOI":"10.18653\/v1\/2020.louhi-1.5"},{"key":"8024_CR9","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1016\/j.acra.2022.06.024","volume":"30","author":"D Zhang","year":"2023","unstructured":"Zhang D, et al. Utility of a rule-based algorithm in the assessment of standardized reporting in PI-RADS. Acad Radiol. 2023;30:1141\u20137. https:\/\/doi.org\/10.1016\/j.acra.2022.06.024.","journal-title":"Acad Radiol"},{"key":"8024_CR10","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1177\/0165551509360123","volume":"36","author":"DC Wimalasuriya","year":"2010","unstructured":"Wimalasuriya DC, Dou D. Ontology-based information extraction: an introduction and a survey of current approaches. J Inf Sci. 2010;36:306\u201323. https:\/\/doi.org\/10.1177\/0165551509360123.","journal-title":"J Inf Sci"},{"key":"8024_CR11","doi-asserted-by":"publisher","unstructured":"Wu S, et al. Benchmarking open-source large language models, GPT-4 and Claude 2 on multiple-choice questions in nephrology. NEJM AI. 2024;1. https:\/\/doi.org\/10.1056\/AIDBP2300092.","DOI":"10.1056\/AIDBP2300092"},{"key":"8024_CR12","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1186\/s12911-022-01843-4","volume":"22","author":"VM D\u2019Anniballe","year":"2022","unstructured":"D\u2019Anniballe VM, et al. Multi-label annotation of text reports from computed tomography of the chest, abdomen, and pelvis using deep learning. BMC Med Inf Decis Mak. 2022;22:435. https:\/\/doi.org\/10.1186\/s12911-022-01843-4.","journal-title":"BMC Med Inf Decis Mak"}],"container-title":["BMC Research Notes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13104-026-08024-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13104-026-08024-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13104-026-08024-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:16:48Z","timestamp":1789993008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13104-026-08024-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":12,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["8024"],"URL":"https:\/\/doi.org\/10.1186\/s13104-026-08024-w","relation":{},"ISSN":["1756-0500"],"issn-type":[{"value":"1756-0500","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"assertion":[{"value":"5 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2026","order":3,"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 approved by the Ethics Committee of the University of W\u00fcrzburg (approval number: 20.02.2024\/ag).","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. The manuscript does not contain any individual person\u2019s data in any form (including individual details, images, or videos).","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"355"}}