{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T19:14:20Z","timestamp":1793042060273,"version":"4.5.0"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004622","name":"KWF Kankerbestrijding","doi-asserted-by":"publisher","award":["14113"],"award-info":[{"award-number":["14113"]}],"id":[{"id":"10.13039\/501100004622","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>A screening-trained deep learning (DL) model (DL1) for pulmonary nodule malignancy probability estimation on CT previously demonstrated good discrimination on a single-centre dataset of incidental nodules. An updated DL model (DL2) was trained on both screening and clinical data. We aimed to test the performance of both models in a multicentre dataset of incidental nodules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>A retrospective, multicentre, case-control dataset of incidental nodules was collected, sampled across size buckets (5\u201310\u2009mm, 10\u201315\u2009mm, 15\u201330\u2009mm), aiming for 10 malignant and 20 benign nodules per bucket and centre, resulting in 270 nodules. Performance was assessed using AUCs and specificity at a fixed sensitivity. AUCs were compared using the DeLong method. Both DL models were compared with the Brock model. Consistent discrimination was investigated by centre-stratified analyses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The multicentre dataset contained 269 nodules (89 malignant) from 231 patients. DL1 and DL2 achieved AUCs of 0.74 and 0.72, respectively, versus 0.63 for Brock (both\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.01). Using a 10% threshold for the Brock model (sensitivity 77.5%), specificity was 60% for both DL models compared with 44% for the Brock model. Centre-specific AUCs for DL1, DL2, and Brock were 0.76, 0.75, and 0.74 (centre 1), 0.72, 0.71, and 0.55 (centre 2), and 0.73, 0.71, and 0.59 (centre 3), respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The DL models outperformed the Brock model on a multicentre, cancer-enriched size-stratified dataset and performed consistently across centres, though prospective validation in representative cohorts with real-world prevalences is needed. The DL model trained with additional clinical data performed equal to the screening-trained model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>How consistent is the performance of a screening-trained deep learning model across multicentre incidental pulmonary nodules, and does an additionally clinically trained model improve performance?<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The two deep learning models showed similar discrimination, outperforming the clinically used Brock model in the pooled cancer-enriched dataset, and consistent performance across multiple centres.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The current study provides evidence of consistent model performance across centres with varying CT characteristics and patient populations within one country, supporting the potential of DL models to classify pulmonary nodules across different clinical settings.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-026-12787-y","type":"journal-article","created":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T14:33:08Z","timestamp":1786199588000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multicentre performance and consistency of two deep learning models for malignancy probability estimation of incidental pulmonary nodules"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7136-7475","authenticated-orcid":false,"given":"Renate","family":"Dinnessen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noa","family":"Antonissen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dr\u00e9","family":"Peeters","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hester A.","family":"Gietema","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michiel T. H. M.","family":"Henkens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Firdaus A. A.","family":"Mohamed Hoesein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ernst Th.","family":"Scholten","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cornelia","family":"Schaefer-Prokop","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colin","family":"Jacobs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"12787_CR1","doi-asserted-by":"publisher","unstructured":"Gould MK, Tang T, Liu ILA et al (2015) Recent trends in the identification of incidental pulmonary nodules. Am J Respir Crit Care Med. https:\/\/doi.org\/10.1164\/rccm.201505-0990oc","DOI":"10.1164\/rccm.201505-0990oc"},{"key":"12787_CR2","doi-asserted-by":"publisher","unstructured":"Hendrix W, Rutten M, Hendrix N et al (2023) Trends in the incidence of pulmonary nodules in chest computed tomography: 10-year results from two Dutch hospitals. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-023-09826-3","DOI":"10.1007\/s00330-023-09826-3"},{"key":"12787_CR3","doi-asserted-by":"publisher","unstructured":"Callister MEJ, Baldwin DR, Akram AR et al (2015) British Thoracic Society guidelines for the investigation and management of pulmonary nodules. Thorax. https:\/\/doi.org\/10.1136\/thoraxjnl-2015-207168","DOI":"10.1136\/thoraxjnl-2015-207168"},{"key":"12787_CR4","doi-asserted-by":"publisher","unstructured":"MacMahon H, Naidich DP, Goo JM et al (2017) Guidelines for management of incidental pulmonary nodules detected on CT images: from the Fleischner Society 2017. Radiology. https:\/\/doi.org\/10.1148\/radiol.2017161659","DOI":"10.1148\/radiol.2017161659"},{"key":"12787_CR5","doi-asserted-by":"publisher","unstructured":"McWilliams A, Tammemagi MC, Mayo JR et al (2013) Probability of cancer in pulmonary nodules detected on first screening CT. N Engl J Med. https:\/\/doi.org\/10.1056\/nejmoa1214726","DOI":"10.1056\/nejmoa1214726"},{"key":"12787_CR6","doi-asserted-by":"publisher","unstructured":"Venkadesh KV, Setio AAA, Schreuder A et al (2021) Deep learning for malignancy risk estimation of pulmonary nodules detected at low-dose screening CT. Radiology. https:\/\/doi.org\/10.1148\/radiol.2021204433","DOI":"10.1148\/radiol.2021204433"},{"key":"12787_CR7","doi-asserted-by":"publisher","unstructured":"Antonissen N, Venkadesh KV, Dinnessen R et al (2025) External test of a deep learning algorithm for pulmonary nodule malignancy risk stratification using European screening data. Radiology. https:\/\/doi.org\/10.1148\/radiol.250874","DOI":"10.1148\/radiol.250874"},{"key":"12787_CR8","doi-asserted-by":"publisher","unstructured":"Massion PP, Antic S, Ather S et al (2020) Assessing the accuracy of a deep learning method to risk stratify indeterminate pulmonary nodules. Am J Respir Crit Care Med. https:\/\/doi.org\/10.1164\/rccm.201903-0505oc","DOI":"10.1164\/rccm.201903-0505oc"},{"key":"12787_CR9","doi-asserted-by":"publisher","unstructured":"Baldwin DR, Gustafson J, Pickup L et al (2020) External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules. Thorax. https:\/\/doi.org\/10.1136\/thoraxjnl-2019-214104","DOI":"10.1136\/thoraxjnl-2019-214104"},{"key":"12787_CR10","doi-asserted-by":"publisher","unstructured":"Wulaningsih W, Villamaria C, Akram A, Benemile J, Croce F, Watkins J (2024) Deep learning models for predicting malignancy risk in CT-detected pulmonary nodules: a systematic review and meta-analysis. Lung. https:\/\/doi.org\/10.1007\/s00408-024-00706-1","DOI":"10.1007\/s00408-024-00706-1"},{"key":"12787_CR11","doi-asserted-by":"publisher","unstructured":"Dinnessen R, Peeters D, Antonissen N et al (2025) Performance of a screening-trained DL model for pulmonary nodule malignancy estimation of incidental clinical nodules. Eur Radiol. https:\/\/doi.org\/10.1007\/S00330-025-11829-1","DOI":"10.1007\/S00330-025-11829-1"},{"key":"12787_CR12","doi-asserted-by":"publisher","unstructured":"Winter A, Aberle DR, Hsu W (2019) External validation and recalibration of the Brock model to predict probability of cancer in pulmonary nodules using NLST data. Thorax. https:\/\/doi.org\/10.1136\/thoraxjnl-2018-212413","DOI":"10.1136\/thoraxjnl-2018-212413"},{"key":"12787_CR13","doi-asserted-by":"publisher","unstructured":"Hendrix W, Hendrix N, Scholten ET et al (2023) Deep learning for the detection of benign and malignant pulmonary nodules in non-screening chest CT scans. Commun Med. https:\/\/doi.org\/10.1038\/s43856-023-00388-5","DOI":"10.1038\/s43856-023-00388-5"},{"key":"12787_CR14","first-page":"69","volume":"24","author":"MM Mukaka","year":"2012","unstructured":"Mukaka MM (2012) A guide to appropriate use of correlation coefficient in medical research. Malawi Med J 24:69\u201371","journal-title":"Malawi Med J"},{"key":"12787_CR15","doi-asserted-by":"publisher","unstructured":"Obreja B, Bosma J, Venkadesh KV, Saghir Z, Prokop M, Jacobs C (2025) Characterizing the impact of training data on generalizability: application in deep learning to estimate lung nodule malignancy risk. Radiol Artif Intell. https:\/\/doi.org\/10.1148\/ryai240636","DOI":"10.1148\/ryai240636"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12787-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-026-12787-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12787-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T14:33:09Z","timestamp":1786199589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-026-12787-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":15,"alternative-id":["12787"],"URL":"https:\/\/doi.org\/10.1007\/s00330-026-12787-y","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"7 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The scientific guarantor of this publication is Colin Jacobs.","order":1,"name":"Ethics","label":"Guarantor","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors of this manuscript declare relationships with the following companies: Cornelia Schaefer-Prokop received speaker fees from Canon and Boehringer and royalties from Thieme and Elsevier unrelated to nodule research; Colin Jacobs receives research grants and royalties to the host institution from MeVis Medical Solutions, Bremen, Germany, and payment for lectures from Canon Medical Systems and Johnson & Johnson. Colin Jacobs is a collaborator in a public-private research project where Radboudumc collaborates with Philips Medical Systems (Best, the Netherlands) and another public-private research project where Radboudumc collaborates with Siemens Healthineers (Erlangen, Germany). He reports no other relationships that are related to the subject matter of the article. The other authors of this manuscript declare no relationship with any companies whose products or services may be related to the subject matter of the article.","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"No complex statistical methods were necessary for this paper.","order":3,"name":"Ethics","label":"Statistics and biometry","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Written informed consent was waived by the Institutional Review Board.","order":4,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Institutional Review Board approval was obtained.","order":5,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Some study subjects or cohorts have been previously reported in Dinnessen et al [\n                      \n                      ]. This concerns 12 nodules in 12 patients from centre 3, selected from the larger dataset according to the eligibility criteria defined in the current study.","order":6,"name":"Ethics","label":"Study subjects or cohorts overlap","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"order":7,"name":"Ethics","label":"Methodology","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}}]}}