{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T19:48:09Z","timestamp":1790884089030,"version":"4.1.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100011699","name":"Siemens Healthineers","doi-asserted-by":"publisher","award":["n\/a - research cooperation"],"award-info":[{"award-number":["n\/a - research cooperation"]}],"id":[{"id":"10.13039\/501100011699","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Manufacturer-defined AI thresholds for chest x-ray (CXR) often lack customization options. Threshold optimization strategies utilizing users\u2019 clinical real-world data along with pathology-enriched validation data may better address subgroup-specific and user-specific needs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>\n                      A pathology-enriched dataset (study cohort, 563 (CXRs)) with pleural effusions, consolidations, pneumothoraces, nodules,\u00a0and unremarkable findings was analysed by an AI system and six reference radiologists. The same AI model was applied to a routine dataset (clinical cohort, 15,786 consecutive routine CXRs). Iterative receiver operating characteristic analysis linked achievable sensitivities (study cohort) to resulting AI alert rates in clinical routine inpatient or outpatient subgroups. \u201cOptimized\u201d thresholds (OTs) were defined by a 1% sensitivity increase leading to more than a 1% rise in AI alert rates. Threshold comparisons (OTs\n                      <jats:italic>versus<\/jats:italic>\n                      AI vendor\u2019s default thresholds (AIDT)\n                      <jats:italic>versus<\/jats:italic>\n                      Youden\u2019s thresholds) were based on 400 clinical cohort cases with expert radiologists\u2019 reference.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>AIDTs, OTs, and Youden\u2019s thresholds varied across scenarios, with OTs differing based on tailoring for inpatient or outpatient CXRs. AIDT lowering most reasonably improved sensitivity for pleural effusion, with increases from 46.8% (AIDT) to 87.2% (OT) for outpatients and from 76.3% (AIDT) to 93.5% (OT) for inpatients; similar trends appeared for consolidations. Conversely, regarding inpatient nodule detection, increasing the threshold improved accuracy from 69.5% (AIDT) to 82.5% (OT) without compromising sensitivity. Graphical analysis supports threshold selection by illustrating estimated sensitivities and clinical routine AI alert rates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An innovative, subgroup-specific AI threshold optimization is proposed, automatically implemented and transferable to other AI algorithms and varying clinical subgroup settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Individually customizing thresholds tailored to specific medical experts\u2019 needs and patient subgroup characteristics is promising and may enhance diagnostic accuracy and the clinical acceptance of diagnostic AI algorithms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Customizing AI thresholds individually addresses specific user\/patient subgroup needs.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The presented approach utilizes pathology-enriched and real-world subgroup data for optimization.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Potential is shown by comparing individualized thresholds with vendor defaults.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Distinct thresholds for in- and outpatient CXR AI analysis may improve perception.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The automated pipeline methodology is transferable to other AI models or subgroups.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-025-00632-8","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T04:38:59Z","timestamp":1758515939000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Threshold optimization in AI chest radiography analysis: integrating real-world data and clinical subgroups"],"prefix":"10.1186","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4849-8034","authenticated-orcid":false,"given":"Jan","family":"Rudolph","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Huemmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Preuhs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Buizza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Dinkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanessa","family":"Koliogiannis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Fink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophia Samira","family":"Goller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Schwarze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurice","family":"Heimer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boj Friedrich","family":"Hoppe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Liebig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Ricke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bastian Oliver","family":"Sabel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Rueckel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"632_CR1","doi-asserted-by":"publisher","first-page":"4374","DOI":"10.1007\/s00330-024-11339-6","volume":"5","author":"S Lee","year":"2025","unstructured":"Lee S, Youn J, Kim H et al (2025) CXR-LLaVA: a multimodal large language model for interpreting chest x-ray images. Eur Radiol 5:4374\u20134386. https:\/\/doi.org\/10.1007\/s00330-024-11339-6","journal-title":"Eur Radiol"},{"key":"632_CR2","doi-asserted-by":"publisher","unstructured":"Kazemzadeh S, Kiraly AP, Nabulsi Z et al (2024) Prospective multi-site validation of AI to detect tuberculosis and chest x-ray abnormalities. NEJM AI. https:\/\/doi.org\/10.1056\/aioa2400018","DOI":"10.1056\/aioa2400018"},{"key":"632_CR3","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230981","volume":"310","author":"KG van Leeuwen","year":"2024","unstructured":"van Leeuwen KG, Schalekamp S, Rutten MJCM et al (2024) Comparison of commercial AI software performance for radiograph lung nodule detection and bone age prediction. Radiology 310:e230981. https:\/\/doi.org\/10.1148\/radiol.230981","journal-title":"Radiology"},{"key":"632_CR4","doi-asserted-by":"publisher","first-page":"00131","DOI":"10.1016\/j.chest.2024.01.039","volume":"S0012-3692","author":"J Rudolph","year":"2024","unstructured":"Rudolph J, Huemmer C, Preuhs A et al (2024) Nonradiology health-care professionals significantly benefit from AI assistance in emergency-related chest radiography interpretation. Chest S0012-3692:00131\u201300134. https:\/\/doi.org\/10.1016\/j.chest.2024.01.039","journal-title":"Chest"},{"key":"632_CR5","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231236","volume":"308","author":"L Lind Plesner","year":"2023","unstructured":"Lind Plesner L, M\u00fcller FC, Brejneb\u00f8l MW et al (2023) Commercially available chest radiograph AI tools for detecting airspace disease, pneumothorax, and pleural effusion. Radiology 308:e231236. https:\/\/doi.org\/10.1148\/radiol.231236","journal-title":"Radiology"},{"key":"632_CR6","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1056\/NEJMra2301725","volume":"388","author":"P Rajpurkar","year":"2023","unstructured":"Rajpurkar P, Lungren MP (2023) The current and future state of AI interpretation of medical images. N Engl J Med 388:1981\u20131990. https:\/\/doi.org\/10.1056\/NEJMra2301725","journal-title":"N Engl J Med"},{"key":"632_CR7","doi-asserted-by":"publisher","first-page":"847","DOI":"10.3348\/kjr.2022.0193","volume":"23","author":"S Lee","year":"2022","unstructured":"Lee S, Shin HJ, Kim S, Kim E-K (2022) Successful implementation of an artificial intelligence-based computer-aided detection system for chest radiography in daily clinical practice. Korean J Radiol 23:847\u2013852. https:\/\/doi.org\/10.3348\/kjr.2022.0193","journal-title":"Korean J Radiol"},{"key":"632_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.108774","volume":"123","author":"G Chassagnon","year":"2020","unstructured":"Chassagnon G, Vakalopoulou M, Paragios N, Revel M-P (2020) Artificial intelligence applications for thoracic imaging. Eur J Radiol 123:108774. https:\/\/doi.org\/10.1016\/j.ejrad.2019.108774","journal-title":"Eur J Radiol"},{"key":"632_CR9","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-018-0544-y","volume":"17","author":"C Qin","year":"2018","unstructured":"Qin C, Yao D, Shi Y, Song Z (2018) Computer-aided detection in chest radiography based on artificial intelligence: a survey. Biomed Eng Online 17:113. https:\/\/doi.org\/10.1186\/s12938-018-0544-y","journal-title":"Biomed Eng Online"},{"key":"632_CR10","doi-asserted-by":"publisher","unstructured":"Johnson A, Pollard T, Mark R, Berkowitz S, Horng S (2024) MIMIC-CXR database (version 2.1.0). PhysioNet. RRID:SCR_007345. https:\/\/doi.org\/10.13026\/4jqj-jw95","DOI":"10.13026\/4jqj-jw95"},{"key":"632_CR11","doi-asserted-by":"publisher","unstructured":"Wang X, Peng Y, Lu L et al (2017) ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 3462\u20133471, https:\/\/doi.org\/10.1109\/CVPR.2017.369","DOI":"10.1109\/CVPR.2017.369"},{"key":"632_CR12","doi-asserted-by":"publisher","unstructured":"Irvin J, Rajpurkar P, Ko M et al (2019) CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1901.07031","DOI":"10.48550\/arXiv.1901.07031"},{"key":"632_CR13","doi-asserted-by":"publisher","unstructured":"Rajpurkar P, Irvin J, Zhu K et al (2017) CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1711.05225","DOI":"10.48550\/arXiv.1711.05225"},{"key":"632_CR14","doi-asserted-by":"publisher","first-page":"e605","DOI":"10.1016\/S2589-7500(24)00118-3","volume":"6","author":"ZZ Qin","year":"2024","unstructured":"Qin ZZ, Van der Walt M, Moyo S et al (2024) Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software. Lancet Digit Health 6:e605\u2013e613. https:\/\/doi.org\/10.1016\/S2589-7500(24)00118-3","journal-title":"Lancet Digit Health"},{"key":"632_CR15","doi-asserted-by":"publisher","first-page":"e58413","DOI":"10.2196\/58413","volume":"26","author":"WY Chung","year":"2024","unstructured":"Chung WY, Yoon J, Yoon D et al (2024) Development and validation of deep learning-based infectivity prediction in pulmonary tuberculosis through chest radiography: retrospective study. J Med Internet Res 26:e58413. https:\/\/doi.org\/10.2196\/58413","journal-title":"J Med Internet Res"},{"key":"632_CR16","doi-asserted-by":"publisher","first-page":"e2229289","DOI":"10.1001\/jamanetworkopen.2022.29289","volume":"5","author":"JS Ahn","year":"2022","unstructured":"Ahn JS, Ebrahimian S, McDermott S et al (2022) Association of artificial intelligence-aided chest radiograph interpretation with reader performance and efficiency. JAMA Netw Open 5:e2229289. https:\/\/doi.org\/10.1001\/jamanetworkopen.2022.29289","journal-title":"JAMA Netw Open"},{"key":"632_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-16514-7","volume":"12","author":"J Rudolph","year":"2022","unstructured":"Rudolph J, Schachtner B, Fink N et al (2022) Clinically focused multi-cohort benchmarking as a tool for external validation of artificial intelligence algorithm performance in basic chest radiography analysis. Sci Rep 12:12764. https:\/\/doi.org\/10.1038\/s41598-022-16514-7","journal-title":"Sci Rep"},{"key":"632_CR18","doi-asserted-by":"publisher","first-page":"e2141096","DOI":"10.1001\/jamanetworkopen.2021.41096","volume":"4","author":"F Homayounieh","year":"2021","unstructured":"Homayounieh F, Digumarthy S, Ebrahimian S et al (2021) An artificial intelligence-based chest x-ray model on human nodule detection accuracy from a multicenter study. JAMA Netw Open 4:e2141096. https:\/\/doi.org\/10.1001\/jamanetworkopen.2021.41096","journal-title":"JAMA Netw Open"},{"key":"632_CR19","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1148\/radiol.2533081632","volume":"253","author":"J Shiraishi","year":"2009","unstructured":"Shiraishi J, Pesce LL, Metz CE, Doi K (2009) Experimental design and data analysis in receiver operating characteristic studies: lessons learned from reports in radiology from 1997 to 2006. Radiology 253:822\u2013830. https:\/\/doi.org\/10.1148\/radiol.2533081632","journal-title":"Radiology"},{"key":"632_CR20","doi-asserted-by":"publisher","first-page":"07TR01","DOI":"10.1088\/1361-6560\/aab4b1","volume":"63","author":"NA Obuchowski","year":"2018","unstructured":"Obuchowski NA, Bullen JA (2018) Receiver operating characteristic (ROC) curves: review of methods with applications in diagnostic medicine. Phys Med Biol 63:07TR01. https:\/\/doi.org\/10.1088\/1361-6560\/aab4b1","journal-title":"Phys Med Biol"},{"key":"632_CR21","first-page":"627","volume":"4","author":"K Hajian-Tilaki","year":"2013","unstructured":"Hajian-Tilaki K (2013) Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian J Intern Med 4:627\u2013635","journal-title":"Caspian J Intern Med"},{"key":"632_CR22","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1093\/aje\/kwj063","volume":"163","author":"NJ Perkins","year":"2006","unstructured":"Perkins NJ, Schisterman EF (2006) The inconsistency of \u201coptimal\u201d cutpoints obtained using two criteria based on the receiver operating characteristic curve. Am J Epidemiol 163:670\u2013675. https:\/\/doi.org\/10.1093\/aje\/kwj063","journal-title":"Am J Epidemiol"},{"key":"632_CR23","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1002\/bimj.200410135","volume":"47","author":"R Fluss","year":"2005","unstructured":"Fluss R, Faraggi D, Reiser B (2005) Estimation of the Youden index and its associated cutoff point. Biom J 47:458\u2013472. https:\/\/doi.org\/10.1002\/bimj.200410135","journal-title":"Biom J"},{"key":"632_CR24","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1097\/RLI.0000000000000813","volume":"57","author":"J Rudolph","year":"2022","unstructured":"Rudolph J, Huemmer C, Ghesu F-C et al (2022) Artificial intelligence in chest radiography reporting accuracy: added clinical value in the emergency unit setting without 24\/7 radiology coverage. Invest Radiol 57:90\u201398. https:\/\/doi.org\/10.1097\/RLI.0000000000000813","journal-title":"Invest Radiol"},{"key":"632_CR25","doi-asserted-by":"publisher","first-page":"1868","DOI":"10.3390\/diagnostics11101868","volume":"11","author":"J Rudolph","year":"2021","unstructured":"Rudolph J, Fink N, Dinkel J et al (2021) Interpretation of thoracic radiography shows large discrepancies depending on the qualification of the physician-quantitative evaluation of interobserver agreement in a representative emergency department scenario. Diagnostics (Basel) 11:1868. https:\/\/doi.org\/10.3390\/diagnostics11101868","journal-title":"Diagnostics (Basel)"},{"key":"632_CR26","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. Preprint at: https:\/\/doi.org\/10.48550\/arXiv.1901.07031","DOI":"10.48550\/arXiv.1901.07031"},{"key":"632_CR27","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1097\/RLI.0000000000000707","volume":"55","author":"J Rueckel","year":"2020","unstructured":"Rueckel J, Trappmann L, Schachtner B et al (2020) Impact of confounding thoracic tubes and pleural dehiscence extent on artificial intelligence pneumothorax detection in chest radiographs. Invest Radiol 55:792\u2013798. https:\/\/doi.org\/10.1097\/RLI.0000000000000707","journal-title":"Invest Radiol"},{"key":"632_CR28","doi-asserted-by":"publisher","first-page":"7888","DOI":"10.1007\/s00330-021-07833-w","volume":"31","author":"J Rueckel","year":"2021","unstructured":"Rueckel J, Huemmer C, Fieselmann A et al (2021) Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training. Eur Radiol 31:7888\u20137900. https:\/\/doi.org\/10.1007\/s00330-021-07833-w","journal-title":"Eur Radiol"},{"key":"632_CR29","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","volume":"6","author":"AS Tejani","year":"2024","unstructured":"Tejani AS, Klontzas ME, Gatti AA et al (2024) Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update. Radiol Artif Intell 6:e240300. https:\/\/doi.org\/10.1148\/ryai.240300","journal-title":"Radiol Artif Intell"},{"key":"632_CR30","unstructured":"R Core Team (2022) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna"},{"key":"632_CR31","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden WJ (1950) Index for rating diagnostic tests. Cancer 3:32\u201335","journal-title":"Cancer"},{"key":"632_CR32","doi-asserted-by":"publisher","first-page":"1S","DOI":"10.1378\/chest.108.2_supplement.1s","volume":"108","author":"DE Craven","year":"1995","unstructured":"Craven DE, Steger KA (1995) Epidemiology of nosocomial pneumonia. New perspectives on an old disease. Chest 108:1S\u201316S. https:\/\/doi.org\/10.1378\/chest.108.2_supplement.1s","journal-title":"Chest"},{"key":"632_CR33","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-03091-2","volume":"24","author":"R Zaragoza","year":"2020","unstructured":"Zaragoza R, Vidal-Cort\u00e9s P, Aguilar G et al (2020) Update of the treatment of nosocomial pneumonia in the ICU. Crit Care 24:383. https:\/\/doi.org\/10.1186\/s13054-020-03091-2","journal-title":"Crit Care"},{"key":"632_CR34","doi-asserted-by":"publisher","first-page":"249","DOI":"10.21037\/qims-24-1627","volume":"15","author":"W Shi","year":"2025","unstructured":"Shi W, Hu Y, Sun Y et al (2025) Exploration of optimal thresholds for predicting the invasive nature of stage T1 lung adenocarcinoma using artificial intelligence-based 3D solid component volume segmentation. Quant Imaging Med Surg 15:249\u2013258. https:\/\/doi.org\/10.21037\/qims-24-1627","journal-title":"Quant Imaging Med Surg"},{"key":"632_CR35","doi-asserted-by":"publisher","first-page":"8988","DOI":"10.21037\/qims-24-1328","volume":"14","author":"W Shi","year":"2024","unstructured":"Shi W, Hu Y, Sun Y et al (2024) Exploring the optimal threshold of 3D consolidation tumor ratio value segmentation based on artificial intelligence for predicting the invasive degree of T1 lung adenocarcinoma. Quant Imaging Med Surg 14:8988\u20138998. https:\/\/doi.org\/10.21037\/qims-24-1328","journal-title":"Quant Imaging Med Surg"},{"key":"632_CR36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-82775-z","volume":"14","author":"HJ Shin","year":"2024","unstructured":"Shin HJ, Han K, Son N-H et al (2024) Optimizing adult-oriented artificial intelligence for pediatric chest radiographs by adjusting operating points. Sci Rep 14:31329. https:\/\/doi.org\/10.1038\/s41598-024-82775-z","journal-title":"Sci Rep"},{"key":"632_CR37","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1186\/s41747-023-00386-1","volume":"7","author":"H Shin","year":"2023","unstructured":"Shin H, Kim T, Park J et al (2023) Pulmonary abnormality screening on chest x-rays from different machine specifications: a generalized AI-based image manipulation pipeline. Eur Radiol Exp 7:68. https:\/\/doi.org\/10.1186\/s41747-023-00386-1","journal-title":"Eur Radiol Exp"},{"key":"632_CR38","doi-asserted-by":"publisher","first-page":"270","DOI":"10.3390\/jimaging9120270","volume":"9","author":"A Wollek","year":"2023","unstructured":"Wollek A, Hyska S, Sabel B et al (2023) WindowNet: learnable Windows for chest X-ray classification. J Imaging 9:270. https:\/\/doi.org\/10.3390\/jimaging9120270","journal-title":"J Imaging"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00632-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-025-00632-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00632-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T12:14:26Z","timestamp":1758716066000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurradiolexp.springeropen.com\/articles\/10.1186\/s41747-025-00632-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["632"],"URL":"https:\/\/doi.org\/10.1186\/s41747-025-00632-8","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"8 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study obtained approval from the Ethics Committee of the Medical Faculty of Ludwig-Maximilians-University Munich (approval number 19-541). All methods were performed in accordance with the relevant guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The Ethics Committee of the Medical Faculty of Ludwig-Maximilians-University Munich waived informed consent due to the retrospective nature of the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"CH, AP, and GB are affiliated with Siemens Healthineers. The remaining authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"95"}}