{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T15:10:14Z","timestamp":1790953814719,"version":"4.1.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"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>Lung cancer is the leading cause of cancer-related mortality. While early detection improves survival, distinguishing malignant from benign pulmonary nodules remains challenging. Artificial intelligence (AI) has been proposed to enhance diagnostic accuracy, but its clinical reliability is still under investigation. Here, we aimed to evaluate the diagnostic performance of AI models in classifying pulmonary nodules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This single-center retrospective study analyzed pulmonary nodules (4\u201330\u2009mm) detected on CT scans, using three AI software models. Sensitivity, specificity, false-positive and false-negative rates were calculated. The diagnostic accuracy was assessed using the area under the receiver operating characteristic (ROC) curve (AUC), with histopathology serving as the gold standard. Subgroup analyses were based on nodule size and histopathological classification. The impact of imaging parameters was evaluated using regression analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A total of 158 nodules (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200930 benign,\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009128 malignant) were analyzed. One AI model classified most nodules as intermediate risk, preventing further accuracy assessment. The other models demonstrated moderate sensitivity (53.1\u201370.3%) but low specificity (46.7\u201366.7%), leading to a high false-positive rate (45.5\u201352.4%). AUC values were between 0.5 and 0.6 (95% CI). Subgroup analyses revealed decreased sensitivity (47.8\u201361.5%) but increased specificity (100%), highlighting inconsistencies. In total, up to 49.0% of the pulmonary nodules were classified as intermediate risk. CT scan type influenced performance (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.03), with better classification accuracy on breath-held CT scans.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI-based software models are not ready for standalone clinical use in pulmonary nodule classification due to low specificity, a high false-negative rate and a high proportion of intermediate-risk classifications.<\/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 accurate are commercially available AI models for the classification of pulmonary nodules compared to the gold standard of histopathology?<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The evaluated AI models demonstrated moderate sensitivity, low specificity and high false-negative rates. Up to 49% of pulmonary nodules were classified as intermediate risk.<\/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 high false-negative rates could influence radiologists\u2019 decision-making, leading to an increased number of interventions or unnecessary surgical procedures.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-025-11845-1","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T16:22:45Z","timestamp":1753460565000},"page":"537-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Diagnostic performance of artificial intelligence models for pulmonary nodule classification: a multi-model evaluation"],"prefix":"10.1007","volume":"36","author":[{"given":"Sarah K.","family":"Herber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8626-4044","authenticated-orcid":false,"given":"Lukas","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Pinto dos Santos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Jorg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Souschek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"B\u00e4uerle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Foersch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Galata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Mildenberger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moritz C.","family":"Halfmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"11845_CR1","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/S2213-2600(24)00428-4","volume":"13","author":"G Luo","year":"2025","unstructured":"Luo G, Zhang Y, Rumgay H et al (2025) Estimated worldwide variation and trends in incidence of lung cancer by histological subtype in 2022 and over time: a population-based study. Lancet Respir Med 13:348\u2013363","journal-title":"Lancet Respir Med"},{"key":"11845_CR2","doi-asserted-by":"crossref","unstructured":"Jeon DS, Kim HC, Kim SH et al (2023) Five-year overall survival and prognostic factors in patients with lung cancer: results from the Korean Association of Lung Cancer Registry (KALC-R) 2015. Cancer Res Treat 55:103\u2013111","DOI":"10.4143\/crt.2022.264"},{"key":"11845_CR3","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1016\/j.chest.2021.12.655","volume":"161","author":"J Huang","year":"2022","unstructured":"Huang J, Deng Y, Tin MS (2022) Distribution, risk factors, and temporal trends for lung cancer incidence and mortality: a global analysis. Chest 161:1101\u20131111","journal-title":"Chest"},{"key":"11845_CR4","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1002\/cac2.12002","volume":"40","author":"A Liu","year":"2020","unstructured":"Liu A, Wang Z, Yang Y et al (2020) Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram. Cancer Commun (Lond) 40:16\u201324","journal-title":"Cancer Commun (Lond)"},{"key":"11845_CR5","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1097\/JS9.0000000000002247","volume":"111","author":"H Zhang","year":"2025","unstructured":"Zhang H, Zhang C, Li L et al (2025) Small pulmonary nodule localization techniques in the era of lung cancer screening: a narrative review. Int J Surg 111:2624\u20132632","journal-title":"Int J Surg"},{"key":"11845_CR6","first-page":"1024","volume":"101","author":"G Schmid-Bindert","year":"2022","unstructured":"Schmid-Bindert G, Vogel-Claussen J, G\u00fctz S et al (2022) Incidental pulmonary nodules\u2014what do we know in 2022. Karger 101:1024\u20131034","journal-title":"Karger"},{"key":"11845_CR7","doi-asserted-by":"publisher","first-page":"170025","DOI":"10.1183\/16000617.0025-2017","volume":"26","author":"AR Larici","year":"2017","unstructured":"Larici AR, Farchione A, Franchi P et al (2017) Lung nodules: size still matters. Eur Respir Rev 26:170025","journal-title":"Eur Respir Rev"},{"key":"11845_CR8","doi-asserted-by":"crossref","unstructured":"Chassagnon G, De Margerie-Mellon C, Vakalopoulou M et al (2023) Artificial intelligence in lung cancer: current applications and perspectives. Jpn J Radiol 41:235\u2013244","DOI":"10.1007\/s11604-022-01359-x"},{"key":"11845_CR9","doi-asserted-by":"crossref","unstructured":"Wang C, Liu Y, Wang F et al (2024) Towards reliable and explainable AI model for pulmonary nodule diagnosis. Biomed Signal Process Control 88:105646","DOI":"10.1016\/j.bspc.2023.105646"},{"key":"11845_CR10","doi-asserted-by":"crossref","unstructured":"de Margerie-Mellon C, Chassagnon G (2023) Artificial intelligence: a critical review of applications for lung nodule and lung cancer. Diagn Interv Imaging 104:11\u201317","DOI":"10.1016\/j.diii.2022.11.007"},{"key":"11845_CR11","unstructured":"AWMF, DKG, DKH (2025) Pr\u00e4vention, Diagnostik, Therapie und Nachsorge des Lungenkarzinoms. Leitlinienprogramm Onkologie der Arbeitsgemeinschaft der Wissenschaftlichen Medizinischen Fachgesellschaften e.V., Deutschen Krebsgesellschaft e.V. und der Stiftung Deutsche Krebshilfe. available at: https:\/\/www.awmf.org\/service\/awmf-aktuell\/praevention-diagnostik-therapie-und-nachsorge-des-lungenkarzinoms-living-guideline-82 (Accessed on 17 July 2025)"},{"key":"11845_CR12","doi-asserted-by":"publisher","first-page":"130","DOI":"10.3390\/biomedicines13010130","volume":"13","author":"LG Stana","year":"2025","unstructured":"Stana LG, Mederle AO, Avram C, Bratosin F, Barata PI (2025) Retrospective analysis comparing Lung-RADS v2022 and British Thoracic Society guidelines for differentiating lung metastases from primary lung cancer. Biomedicines 13:130","journal-title":"Biomedicines"},{"key":"11845_CR13","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s00330-023-10065-9","volume":"34","author":"C Jacobs","year":"2024","unstructured":"Jacobs C (2024) Challenges and outlook in the management of pulmonary nodules detected on CT. Eur Radiol 34:247\u2013249","journal-title":"Eur Radiol"},{"key":"11845_CR14","doi-asserted-by":"publisher","first-page":"103595","DOI":"10.1016\/j.esmoop.2024.103595","volume":"9","author":"S Xu","year":"2024","unstructured":"Xu S, Luo J, Tang W et al (2024) Detecting pulmonary malignancy against benign nodules using noninvasive cell-free DNA fragmentomics assay. ESMO Open 9:103595","journal-title":"ESMO Open"},{"key":"11845_CR15","doi-asserted-by":"publisher","first-page":"4344","DOI":"10.3390\/cancers15174344","volume":"15","author":"M Cellina","year":"2023","unstructured":"Cellina M, Cacioppa LM, C\u00e8 M et al (2023) Artificial intelligence in lung cancer screening: the future is now. Cancers (Basel) 15:4344","journal-title":"Cancers (Basel)"},{"key":"11845_CR16","doi-asserted-by":"crossref","unstructured":"Kasaudhan H, Kumar Shukla K, Kushwaha R, Sharma K, Gupta U, Sharma A (2024) Early detection and analysis of lung cancer using artificial intelligence. In: 2024 IEEE international conference on computing, power and communication technologies. IEEE, Greater Noida","DOI":"10.1109\/IC2PCT60090.2024.10486335"},{"key":"11845_CR17","first-page":"336","volume":"22","author":"X Li","year":"2019","unstructured":"Li X, Guo F, Zhou Z et al (2019) Performance of deep-learning-based artificial intelligence on detection of pulmonary nodules in chest CT. Chin J Lung Cancer 22:336\u2013340","journal-title":"Chin J Lung Cancer"},{"key":"11845_CR18","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.21037\/tlcr-2020-lcs-06","volume":"10","author":"A Schreuder","year":"2021","unstructured":"Schreuder A, Schaefer-Prokop CM, Scholten ET, Jacobs C (2021) Artificial intelligence for detection and characterization of pulmonary nodules in lung cancer CT screening: ready for practice? Transl Lung Cancer Res 10:2378\u20132388","journal-title":"Transl Lung Cancer Res"},{"key":"11845_CR19","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/S0140-6736(22)01694-4","volume":"401","author":"SJ Adams","year":"2023","unstructured":"Adams SJ, Stone E, Baldwin DR, Vliegenthart R, Lee P, Fintelmann FJ (2023) Lung cancer screening. Lancet 401:390\u2013408","journal-title":"Lancet"},{"key":"11845_CR20","doi-asserted-by":"publisher","first-page":"2435","DOI":"10.3390\/diagnostics12102435","volume":"12","author":"PA Grenier","year":"2022","unstructured":"Grenier PA, Brun AL, Mellot F (2022) The potential role of artificial intelligence in lung cancer screening using low-dose computed tomography. Diagnostics (Basel) 12:2435","journal-title":"Diagnostics (Basel)"},{"key":"11845_CR21","doi-asserted-by":"publisher","first-page":"3536","DOI":"10.3390\/jcm12103536","volume":"12","author":"LJS Ewals","year":"2023","unstructured":"Ewals LJS, van der Wulp K, van den Borne BEEM et al (2023) The effects of artificial intelligence assistance on the radiologists\u2019 assessment of lung nodules on CT scans: a systematic review. J Clin Med 12:3536","journal-title":"J Clin Med"},{"key":"11845_CR22","doi-asserted-by":"publisher","unstructured":"Abbas M, Usama Khalid Bukhari S, Syed A, Shah S (2020) The histopathological diagnosis of adenocarcinoma & squamous cells carcinoma of lungs by artificial intelligence: a comparative study of convolutional neural networks. Preprint at https:\/\/doi.org\/10.1101\/2020.05.02.20044602","DOI":"10.1101\/2020.05.02.20044602"},{"key":"11845_CR23","doi-asserted-by":"publisher","first-page":"e7140","DOI":"10.1002\/cam4.7140","volume":"13","author":"W Quanyang","year":"2024","unstructured":"Quanyang W, Yao H, Sicong W (2024) Artificial intelligence in lung cancer screening: detection, classification, prediction, and prognosis. Cancer Med 13:e7140","journal-title":"Cancer Med"},{"key":"11845_CR24","doi-asserted-by":"publisher","first-page":"e2017135","DOI":"10.1001\/jamanetworkopen.2020.17135","volume":"3","author":"H Yoo","year":"2020","unstructured":"Yoo H, Kim KH, Singh R, Digumarthy SR, Kalra MK (2020) Validation of a deep learning algorithm for the detection of malignant pulmonary nodules in chest radiographs. JAMA Netw 3:e2017135","journal-title":"JAMA Netw"},{"key":"11845_CR25","doi-asserted-by":"crossref","unstructured":"Hu W, Zhang J, Zhou D et al (2024) A comparison study of artificial intelligence performance against physicians in benign\u2013malignant classification of pulmonary nodules. Oncologie 26:581\u2013586","DOI":"10.1515\/oncologie-2023-0319"},{"key":"11845_CR26","first-page":"e2017156","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 (Lond) 3:e2017156","journal-title":"Commun Med (Lond)"},{"key":"11845_CR27","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.clinimag.2023.03.017","volume":"99","author":"F Chutivanidchayakul","year":"2023","unstructured":"Chutivanidchayakul F, Suwatanapongched T, Petnak T (2023) Clinical and chest radiographic features of missed lung cancer and their association with patient outcomes. Clin Imaging 99:73\u201381","journal-title":"Clin Imaging"},{"key":"11845_CR28","doi-asserted-by":"publisher","first-page":"e230506","DOI":"10.1148\/ryai.230506","volume":"7","author":"TZ Li","year":"2025","unstructured":"Li TZ, Xu K, Krishnan A et al (2025) Performance of lung cancer prediction models for screening-detected, incidental, and biopsied pulmonary nodules. Radiol Artif Intell 7:e230506","journal-title":"Radiol Artif Intell"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11845-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-025-11845-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-025-11845-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T14:02:53Z","timestamp":1765980173000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-025-11845-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["11845"],"URL":"https:\/\/doi.org\/10.1007\/s00330-025-11845-1","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,25]]},"assertion":[{"value":"2 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2025","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 M.C.H.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The Department of Diagnostic and Interventional Radiology of the Medical Center of the Johannes Gutenberg-University (S.H., L.M., D.P.d.S., T.J., F.S., T.B., P.M., M.H.) receives institutional research support from Siemens Healthineers, unrelated to the current work. L.M. has received speaker honoraria from Bayer AG. D.P.d.S.: consultation fees from Cook Medical, speaker honoraria from Bayer AG, author honoraria from Amboss GmbH, serves as deputy editor for\n                      European Radiology\n                      , and is a member of the Scientific Editorial Board of\n                      Insights into Imaging\n                      \u2014as such, he has not participated in the selection or review processes for this article. S.F. has received speaker honoraria from BMS and MSD. The remaining authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"One of the authors has significant statistical expertise. No complex statistical methods were necessary for this paper.","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.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"There were no overlaps with previously published studies.","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}