{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:15:40Z","timestamp":1783736140012,"version":"3.55.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T00:00:00Z","timestamp":1783728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T00:00:00Z","timestamp":1783728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100020098","name":"Innovative Health Initiative","doi-asserted-by":"publisher","award":["101112053"],"award-info":[{"award-number":["101112053"]}],"id":[{"id":"10.13039\/100020098","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>Objective<\/jats:title>\n                    <jats:p>\n                      The current BTS guidelines recommend evaluation of suspicious pulmonary nodules using [\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG-PET\/CT imaging, followed by Herder model risk stratification. However, it is based on limited imaging features, which may limit diagnostic accuracy. This study aims to develop a PET\/CT-based deep learning (DL) model for malignancy probability estimation (AITO-PETCT-MP) and compare its performance to the Herder model and clinician performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>In a single-center retrospective study, we collected 533 indeterminate pulmonary nodules (268 malignant) with a mean diameter of 18.4\u2009mm (SD\u2009\u00b1\u200912.1) in 436 patients. Histopathological malignancy confirmation or a minimum 2-year benign national cancer registry follow-up served as the reference standard. Model diagnostic performance was compared against the Herder model and seven clinicians in a reader study on a test set of 161 nodules (80 malignant).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      AITO-PETCT-MP achieved an AUC of 0.78 [95% CI: 0.70\u20130.85] compared to the Herder model: AUC\u2009=\u20090.73 [0.65\u20130.80] (non-inferiority:\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.005). On average, experienced clinicians achieved an AUC of 0.80 [0.75\u20130.85]. Stratifying into BTS follow-up categories, the Herder model referred more benign nodules for potential direct treatment (26\/81) than AITO-PETCT-MP and clinicians (both 3\/81), while AITO-PETCT-MP and clinicians assigned more malignant cases to CT surveillance instead of direct treatment.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AITO-PETCT-MP demonstrated non-inferior performance to the guideline-recommended Herder model, while only using imaging data. Diagnostic performance fell in the performance range of seven clinicians. Differences in BTS follow-up recommendations between the Herder model and clinicians suggest a difference in patient management compared to current clinical practice.<\/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 well can an imaging-only deep learning model estimate pulmonary nodule malignancy probability on [<\/jats:italic>\n                      <jats:sup>\n                        <jats:italic>18<\/jats:italic>\n                      <\/jats:sup>\n                      <jats:italic>F]FDG-PET\/CT compared to the established Herder model and expert clinicians?<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The model (AITO-PETCT-MP) performed non-inferior to the Herder model (AUC 0.78 vs 0.73, p\u2009=\u20090.005) and comparably to seven expert readers (AUC 0.74\u20130.87).<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>BTS-based follow-up stratification showed the Herder model referred more benign nodules to potential direct treatment than clinicians and AITO-PETCT-MP, while assigning fewer malignant cases to surveillance. This suggests a difference between Herder recommendations and current clinical practice.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-026-12744-9","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T01:59:48Z","timestamp":1783735188000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based malignancy probability estimation of pulmonary nodules in PET\/CT imaging"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9396-0204","authenticated-orcid":false,"given":"Lars","family":"Leijten","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik H. J. G.","family":"Aarntzen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roel L. J.","family":"Verhoeven","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrienne H.","family":"Brouwers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bram","family":"Geurts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes A.","family":"van der Heide","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klaas Pieter","family":"Koopmans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walter","family":"Noordzij","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilles N.","family":"Stormezand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik H. F. M.","family":"van der Heijden","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":[[2026,7,11]]},"reference":[{"key":"12744_CR1","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1056\/NEJMoa1102873","volume":"365","author":"DR Aberle","year":"2011","unstructured":"Aberle DR, Adams AM, Berg CD et al (2011) Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 365:395\u2013409","journal-title":"N Engl J Med"},{"key":"12744_CR2","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1093\/annonc\/mdz117","volume":"30","author":"U Pastorino","year":"2019","unstructured":"Pastorino U, Silva M, Sestini S et al (2019) Prolonged lung cancer screening reduced 10-year mortality in the MILD trial: new confirmation of lung cancer screening efficacy. Ann Oncol 30:1162\u20131169","journal-title":"Ann Oncol"},{"key":"12744_CR3","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1056\/NEJMoa1911793","volume":"382","author":"HJ de Koning","year":"2020","unstructured":"de Koning HJ, van Der Aalst CM, de Jong PA et al (2020) Reduced lung-cancer mortality with volume CT screening in a randomized trial. N Engl J Med 382:503\u2013513","journal-title":"N Engl J Med"},{"key":"12744_CR4","doi-asserted-by":"publisher","first-page":"8279","DOI":"10.1007\/s00330-023-09826-3","volume":"33","author":"W Hendrix","year":"2023","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 33:8279\u20138288","journal-title":"Eur Radiol"},{"key":"12744_CR5","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1001\/jama.2021.24287","volume":"327","author":"PJ Mazzone","year":"2022","unstructured":"Mazzone PJ, Lam L (2022) Evaluating the patient with a pulmonary nodule: a review. JAMA 327:264\u2013273","journal-title":"JAMA"},{"key":"12744_CR6","doi-asserted-by":"publisher","first-page":"ii1","DOI":"10.1136\/thoraxjnl-2015-207168","volume":"70","author":"M Callister","year":"2015","unstructured":"Callister M, Baldwin D, Akram A et al (2015) British Thoracic Society guidelines for the investigation and management of pulmonary nodules: accredited by NICE. Thorax 70:ii1\u2013ii54","journal-title":"Thorax"},{"key":"12744_CR7","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1056\/NEJMoa1214726","volume":"369","author":"A McWilliams","year":"2013","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 369:910\u2013919","journal-title":"N Engl J Med"},{"key":"12744_CR8","doi-asserted-by":"publisher","first-page":"2490","DOI":"10.1378\/chest.128.4.2490","volume":"128","author":"GJ Herder","year":"2005","unstructured":"Herder GJ, Van Tinteren H, Golding RP et al (2005) Clinical prediction model to characterize pulmonary nodules: validation and added value of 18 F-fluorodeoxyglucose positron emission tomography. Chest 128:2490\u20132496","journal-title":"Chest"},{"key":"12744_CR9","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1038\/s41591-019-0447-x","volume":"25","author":"D Ardila","year":"2019","unstructured":"Ardila D, Kiraly AP, Bharadwaj S et al (2019) End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 25:954\u2013961","journal-title":"Nat Med"},{"key":"12744_CR10","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1136\/thoraxjnl-2019-214104","volume":"75","author":"DR Baldwin","year":"2020","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 75:306\u2013312","journal-title":"Thorax"},{"key":"12744_CR11","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1200\/JCO.22.01345","volume":"41","author":"PG Mikhael","year":"2023","unstructured":"Mikhael PG, Wohlwend J, Yala A et al (2023) Sybil: a validated deep learning model to predict future lung cancer risk from a single low-dose chest computed tomography. J Clin Oncol 41:2191\u20132200","journal-title":"J Clin Oncol"},{"key":"12744_CR12","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1148\/radiol.2021204433","volume":"300","author":"KV Venkadesh","year":"2021","unstructured":"Venkadesh KV, Setio AA, Schreuder A et al (2021) Deep learning for malignancy risk estimation of pulmonary nodules detected at low-dose screening CT. Radiology 300:438\u2013447","journal-title":"Radiology"},{"key":"12744_CR13","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s13139-023-00821-6","volume":"58","author":"VM Alves","year":"2024","unstructured":"Alves VM, dos Santos Cardoso J, Gama J (2024) Classification of pulmonary nodules in 2-[18F] FDG PET\/CT images with a 3D convolutional neural network. Nucl Med Mol Imaging 58:9\u201324","journal-title":"Nucl Med Mol Imaging"},{"key":"12744_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.773041","volume":"9","author":"Y-C Lai","year":"2022","unstructured":"Lai Y-C, Wu K-C, Tseng N-C et al (2022) Differentiation between malignant and benign pulmonary nodules by using automated three-dimensional high-resolution representation learning with fluorodeoxyglucose positron emission tomography-computed tomography. Front Med 9:773041","journal-title":"Front Med"},{"key":"12744_CR15","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1097\/RLU.0000000000003661","volume":"46","author":"Y-J Park","year":"2021","unstructured":"Park Y-J, Choi D, Choi JY, Hyun SH (2021) Performance evaluation of a deep learning system for differential diagnosis of lung cancer with conventional CT and FDG PET\/CT using transfer learning and metadata. Clin Nucl Med 46:635\u2013640","journal-title":"Clin Nucl Med"},{"key":"12744_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40658-021-00423-1","volume":"8","author":"X Shao","year":"2021","unstructured":"Shao X, Niu R, Shao X et al (2021) Application of dual-stream 3D convolutional neural network based on 18 F-FDG PET\/CT in distinguishing benign and invasive adenocarcinoma in ground-glass lung nodules. EJNMMI Phys 8:1\u201313","journal-title":"EJNMMI Phys"},{"key":"12744_CR17","doi-asserted-by":"publisher","first-page":"1802","DOI":"10.1111\/1759-7714.14924","volume":"14","author":"X Zhang","year":"2023","unstructured":"Zhang X, Dong X, Saripan MIB et al (2023) Deep learning PET\/CT-based radiomics integrates clinical data: a feasibility study to distinguish between tuberculosis nodules and lung cancer. Thorac Cancer 14:1802\u20131811","journal-title":"Thorac Cancer"},{"key":"12744_CR18","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1491762","volume":"14","author":"Y Sun","year":"2024","unstructured":"Sun Y, Ge X, Niu R et al (2024) PET\/CT radiomics and deep learning in the diagnosis of benign and malignant pulmonary nodules: progress and challenges. Front Oncol 14:1491762","journal-title":"Front Oncol"},{"key":"12744_CR19","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s43856-023-00388-5","volume":"3","author":"W Hendrix","year":"2023","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 3:156","journal-title":"Commun Med"},{"key":"12744_CR20","unstructured":"Subcommittee QF-PCST (2021) Standardized Uptake Value (SUV). RSNA QIBA Wiki. Available via https:\/\/qibawiki.rsna.org\/index.php\/Standardized_Uptake_Value_(SUV) Accessed 30 Mar 2026"},{"key":"12744_CR21","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s00259-014-2961-x","volume":"42","author":"R Boellaard","year":"2015","unstructured":"Boellaard R, Delgado-Bolton R, Oyen WJ et al (2015) FDG PET\/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging 42:328\u2013354","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"12744_CR22","doi-asserted-by":"publisher","first-page":"1817","DOI":"10.2967\/jnumed.115.163055","volume":"56","author":"CS van der Vos","year":"2015","unstructured":"van der Vos CS, Grootjans W, Osborne DR et al (2015) Improving the spatial alignment in PET\/CT using amplitude-based respiration-gated PET and respiration-triggered CT. J Nucl Med 56:1817\u20131822","journal-title":"J Nucl Med"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-026-12744-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T01:59:49Z","timestamp":1783735189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-026-12744-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,11]]},"references-count":22,"alternative-id":["12744"],"URL":"https:\/\/doi.org\/10.1007\/s00330-026-12744-9","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,11]]},"assertion":[{"value":"14 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Colin Jacobs.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare relationships with the following companies: Roel L.J. Verhoeven declares the following: he received no personal fees, but discloses institutional and departmental research contracts with Pentax medical, AstraZeneca, Johnson & Johnson, Philips, Siemens Healthineers, Intuitive, Thirona, and non-commercial grants from EFRO-oost (EU fund), Innovative Health Initiative (EU fund), KWF (national cancer fund), as well as consulting fees from Intuitive, Johnson & Johnson, paid to the institution, travel support from Intuitive and Johnson & Johnson, in-kind support from Philips Medical and Bioncise for the conduct of clinical studies. He is president of the board of the Dutch Society for Technical Physicians (NVvTG, unpaid). Erik H.F.M. van der Heijden declares the following: he received no personal fees but discloses institutional research grants from Pentax medical, AstraZeneca, Johnson & Johnson, Philips, Intuitive, Thirona, and non-commercial grants from EFRO-oost (EU fund) Innovative Health Initiative (EU fund), KWF (national cancer fund), as well as consulting fees paid to the institution from Johnson & Johnson and Siemens Healthineers and Philips Image guided therapies paid to the institution; travel support from Siemens, Philips and Menarini Benelux; speaker fees paid to institution by Janssen-Cilag, Siemens Healthineers, Pentax, Ethicon, Johnson&Johnson, Intuitive, Philips IGT, Menarini and Medtronic; equipment loans from Philips Medical, Pentax Medical, Intuitive Medtronic, Siemens and Ziehm Imaging for eductional and research purposes. He is president and a member of the executive board of the European Association for Bronchology and Interventional Pulmonology (unpaid). Colin Jacobs receives research grants and royalties to the host institution from MeVis Medical Solutions, Bremen, Germany; payment for lectures from Canon Medical Systems and Johnson & Johnson. Colin Jacobs is a collaborator in a public-private research project with Philips Medical Systems (Best, the Netherlands) and in another with Siemens Healthineers (Erlangen, Germany). The other authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"One of the authors has significant statistical expertise.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was waived by the Institutional Review Board.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained (Radboud University Medical Center, CMO2016-3045, project 24011).","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"N\/A.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}