{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:54:29Z","timestamp":1790153669321,"version":"4.0.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Klinikum der Universit\u00e4t M\u00fcnchen"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur J Nucl Med Mol Imaging"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>\n                      This study aims to investigate whether a diagnostic AI model can effectively support lesion detection and staging in non-small cell lung cancer (NSCLC) [\n                      <jats:sup>1<\/jats:sup>\n                      \u2078F]FDG PET\/CT studies, focusing on the distinction between technical segmentation accuracy and clinically meaningful performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective single-centre study, [\n                      <jats:sup>1<\/jats:sup>\n                      \u2078F]FDG PET\/CT scans from 306 treatment-na\u00efve NSCLC patients were reviewed with reference to multidisciplinary team decisions. Tumour lesions were manually segmented for reference and compared with predictions from the top-performing algorithm of the autoPET III challenge. Quantitative segmentation metrics were calculated, and lesion-level errors were assessed for impact on patient-level TNM and UICC staging.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The algorithm achieved a mean Dice Similarity Coefficient (DSC) of 0.64. Lesion-level sensitivity was 95.8% across all patients, with a precision of 87.5%. False positive M-category lesions (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009196) occurred as most frequent error. Of all false positives, 35.7% were benign and 34.7% non-oncologic pathologies. UICC staging matched ground truth in 207\/306 patients, with most discordances due to upstaging (88\/306).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      Clinically driven metrics and cause-based error analysis offer valuable insight into AI segmentation performance. The evaluated model showed excellent lesion sensitivity but a tendency towards systematic overprediction across TNM categories. On a lesion level M-stage false positives and undersegmentation in the hilar region emerged as the main driver of clinically relevant upstaging. Despite promising lesion detection sensitivity, only 67.7% UICC-stagings\u00a0were accurate using\u00a0AI masks, indicating that diagnostic AI may support, though not yet replace, manual lesion evaluation in NSCLC [\n                      <jats:sup>1<\/jats:sup>\n                      \u2078F]FDG PET\/CT.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00259-025-07677-2","type":"journal-article","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T09:26:04Z","timestamp":1763889964000},"page":"3117-3127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial intelligence for TNM staging in NSCLC: a critical appraisal of segmentation utility in [1\u2078F]FDG PET\/CT"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0940-0161","authenticated-orcid":false,"given":"Maurice M.","family":"Heimer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob","family":"Dexl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johanna","family":"Ta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricarda","family":"Ebner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix L.","family":"Herr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leon","family":"Orasanin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Jeblick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa C.","family":"Adams","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalith K. Shiyam","family":"Sundar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amanda","family":"Tufman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rudolf A.","family":"Werner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Sheikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Ricke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Ingrisch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias P.","family":"Fabritius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clemens C.","family":"Cyran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"7677_CR1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s40644-024-00684-w","volume":"24","author":"LK Shiyam Sundar","year":"2024","unstructured":"Shiyam Sundar LK, Gutschmayer S, Maenle M, Beyer T. Extracting value from total-body PET\/CT image data - the emerging role of artificial intelligence. Cancer Imaging. 2024;24:51. https:\/\/doi.org\/10.1186\/s40644-024-00684-w.","journal-title":"Cancer Imaging"},{"key":"7677_CR2","doi-asserted-by":"publisher","first-page":"995","DOI":"10.2967\/jnumed.123.267183","volume":"65","author":"LK Shiyam Sundar","year":"2024","unstructured":"Shiyam Sundar LK, Beyer T. Is automatic tumor segmentation on whole-body (18)F-FDG PET images a clinical reality? J Nucl Med. 2024;65:995\u20137. https:\/\/doi.org\/10.2967\/jnumed.123.267183.","journal-title":"J Nucl Med"},{"key":"7677_CR3","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1053\/j.semnuclmed.2025.02.006","volume":"55","author":"A Safarian","year":"2025","unstructured":"Safarian A, Mirshahvalad SA, Nasrollahi H, Jung T, Pirich C, Arabi H, et al. Impact of [(18)F]FDG PET\/CT radiomics and artificial intelligence in clinical decision making in lung cancer: its current role. Semin Nucl Med. 2025;55:156\u201366. https:\/\/doi.org\/10.1053\/j.semnuclmed.2025.02.006.","journal-title":"Semin Nucl Med"},{"key":"7677_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107880","volume":"243","author":"M Fallahpoor","year":"2024","unstructured":"Fallahpoor M, Chakraborty S, Pradhan B, Faust O, Barua PD, Chegeni H, et al. Deep learning techniques in PET\/CT imaging: a comprehensive review from sinogram to image space. Comput Methods Programs Biomed. 2024;243:107880. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107880.","journal-title":"Comput Methods Programs Biomed"},{"issue":"13626","key":"7677_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-27420-6_1","volume":"2023","author":"V Andrearczyk","year":"2022","unstructured":"Andrearczyk V, Oreiller V, Abobakr M, Akhavanallaf A, Balermpas P, Boughdad S, et al. Overview of the HECKTOR challenge at MICCAI 2022: automatic head and neck tumor segmentation and outcome prediction in PET\/CT. Head Neck Tumor Chall. 2022;2023(13626):1\u201330. https:\/\/doi.org\/10.1007\/978-3-031-27420-6_1.","journal-title":"Head Neck Tumor Chall"},{"key":"7677_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli M, Reinke A, Bakas S, Farahani K, Kopp-Schneider A, Landman BA, et al. The medical segmentation decathlon. Nat Commun. 2022;13:4128. https:\/\/doi.org\/10.1038\/s41467-022-30695-9.","journal-title":"Nat Commun"},{"key":"7677_CR7","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1038\/s42256-024-00912-9","volume":"6","author":"S Gatidis","year":"2024","unstructured":"Gatidis S, Fr\u00fch M, Fabritius MP, Gu S, Nikolaou K, Foug\u00e8re CL, et al. Results from the autoPET challenge on fully automated lesion segmentation in oncologic PET\/CT imaging. Nat Mach Intell. 2024;6:1396\u2013405. https:\/\/doi.org\/10.1038\/s42256-024-00912-9.","journal-title":"Nat Mach Intell"},{"key":"7677_CR8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.09761","author":"M G\u00f3rka","year":"2024","unstructured":"G\u00f3rka M, Jaworek D, Wodzinski M. Deep learning-based segmentation of tumors in pet\/ct volumes: benchmark of different architectures and training strategies. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2404.09761.","journal-title":"arXiv"},{"key":"7677_CR9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. Nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18:203\u201311. https:\/\/doi.org\/10.1038\/s41592-020-01008-z.","journal-title":"Nat Methods"},{"key":"7677_CR10","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2020-000645","author":"D Chardin","year":"2020","unstructured":"Chardin D, Paquet M, Schiappa R, Darcourt J, Bailleux C, Poudenx M, et al. Baseline metabolic tumor volume as a strong predictive and prognostic biomarker in patients with non-small cell lung cancer treated with PD1 inhibitors: a prospective study. J Immunother Cancer. 2020. https:\/\/doi.org\/10.1136\/jitc-2020-000645.","journal-title":"J Immunother Cancer"},{"key":"7677_CR11","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7528971","volume":"2021","author":"W Wen","year":"2021","unstructured":"Wen W, Piao Y, Xu D, Li X. Prognostic value of MTV and TLG of (18)F-FDG PET in patients with stage I and II non-small-cell lung cancer: a meta-analysis. Contrast Media Mol Imaging. 2021;2021:7528971. https:\/\/doi.org\/10.1155\/2021\/7528971.","journal-title":"Contrast Media Mol Imaging"},{"key":"7677_CR12","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s40658-024-00685-5","volume":"11","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Huang W, Jiao H, Kang L. PET radiomics in lung cancer: advances and translational challenges. EJNMMI Phys. 2024;11:81. https:\/\/doi.org\/10.1186\/s40658-024-00685-5.","journal-title":"EJNMMI Phys"},{"key":"7677_CR13","doi-asserted-by":"publisher","first-page":"802","DOI":"10.2967\/jnumed.124.269271","volume":"66","author":"R Boellaard","year":"2025","unstructured":"Boellaard R, Zwezerijnen GJC, Buvat I, Champion L, Hovhannisyan-Baghdasarian N, Orlhac F, et al. Measuring total metabolic tumor volume from (18)F-FDG PET: a reality check. J Nucl Med. 2025;66:802\u20135. https:\/\/doi.org\/10.2967\/jnumed.124.269271.","journal-title":"J Nucl Med"},{"key":"7677_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-022-06096-y","volume":"15","author":"D Muller","year":"2022","unstructured":"Muller D, Soto-Rey I, Kramer F. Towards a guideline for evaluation metrics in medical image segmentation. BMC Res Notes. 2022;15:210. https:\/\/doi.org\/10.1186\/s13104-022-06096-y.","journal-title":"BMC Res Notes"},{"key":"7677_CR15","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.2967\/jnumed.121.263239","volume":"63","author":"AK Jha","year":"2022","unstructured":"Jha AK, Bradshaw TJ, Buvat I, Hatt M, Kc P, Liu C, et al. Nuclear medicine and artificial intelligence: best practices for evaluation (the RELAINCE guidelines). J Nucl Med. 2022;63:1288\u201399. https:\/\/doi.org\/10.2967\/jnumed.121.263239.","journal-title":"J Nucl Med"},{"key":"7677_CR16","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1148\/radiol.2017171920","volume":"286","author":"SH Park","year":"2018","unstructured":"Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology. 2018;286:800\u20139. https:\/\/doi.org\/10.1148\/radiol.2017171920.","journal-title":"Radiology"},{"key":"7677_CR17","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.chest.2024.05.026","volume":"166","author":"FC Detterbeck","year":"2024","unstructured":"Detterbeck FC, Woodard GA, Bader AS, Dacic S, Grant MJ, Park HS, et al. The proposed ninth edition TNM classification of lung cancer. Chest. 2024;166:882\u201395. https:\/\/doi.org\/10.1016\/j.chest.2024.05.026.","journal-title":"Chest"},{"key":"7677_CR18","doi-asserted-by":"publisher","first-page":"7513","DOI":"10.1038\/s41467-023-42811-4","volume":"14","author":"Y Zhong","year":"2023","unstructured":"Zhong Y, Cai C, Chen T, Gui H, Deng J, Yang M, et al. PET\/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer. Nat Commun. 2023;14:7513. https:\/\/doi.org\/10.1038\/s41467-023-42811-4.","journal-title":"Nat Commun"},{"key":"7677_CR19","doi-asserted-by":"publisher","unstructured":"Rokuss M, Kovacs B, Kirchhoff Y, Xiao S, Ulrich C, Maier-Hein KH, et al. FDG to PSMA: A hitchhiker's guide to multitracer, multicenter lesion segmentation in PET\/CT Imaging. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2409.09478.","DOI":"10.48550\/arXiv.2409.09478"},{"key":"7677_CR20","doi-asserted-by":"publisher","unstructured":"Klontzas ME, Groot Lipman KBW, Akinci D' Antonoli T, Andreychenko A, Cuocolo R, Dietzel M, et al. ESR Essentials: common performance metrics in AI-practice recommendations by the European society of medical imaging informatics. Eur Radiol. 2025. https:\/\/doi.org\/10.1007\/s00330-025-11890-w.","DOI":"10.1007\/s00330-025-11890-w"},{"key":"7677_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-024-01836-z","volume":"15","author":"MM Heimer","year":"2024","unstructured":"Heimer MM, Dikhtyar Y, Hoppe BF, Herr FL, Stuber AT, Burkard T, et al. Software-assisted structured reporting and semi-automated TNM classification for NSCLC staging in a multicenter proof of concept study. Insights Imaging. 2024;15:258. https:\/\/doi.org\/10.1186\/s13244-024-01836-z.","journal-title":"Insights Imaging"},{"key":"7677_CR22","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","volume":"30","author":"A Fedorov","year":"2012","unstructured":"Fedorov A, Beichel R, Kalpathy-Cramer J, Finet J, Fillion-Robin JC, Pujol S, et al. 3D slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging. 2012;30:1323\u201341. https:\/\/doi.org\/10.1016\/j.mri.2012.05.001.","journal-title":"Magn Reson Imaging"},{"key":"7677_CR23","doi-asserted-by":"publisher","first-page":"332","DOI":"10.2967\/jnumed.119.238923","volume":"62","author":"SF Barrington","year":"2021","unstructured":"Barrington SF, Zwezerijnen B, de Vet HCW, Heymans MW, Mikhaeel NG, Burggraaff CN, et al. Automated segmentation of baseline metabolic total tumor burden in diffuse large B-cell lymphoma: which method is most successful? A study on behalf of the PETRA consortium. J Nucl Med. 2021;62:332\u20137. https:\/\/doi.org\/10.2967\/jnumed.119.238923.","journal-title":"J Nucl Med"},{"key":"7677_CR24","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.radonc.2021.05.003","volume":"160","author":"MV Sherer","year":"2021","unstructured":"Sherer MV, Lin D, Elguindi S, Duke S, Tan LT, Cacicedo J, et al. Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: a critical review. Radiother Oncol. 2021;160:185\u201391. https:\/\/doi.org\/10.1016\/j.radonc.2021.05.003.","journal-title":"Radiother Oncol"},{"key":"7677_CR25","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41592-023-02151-z","volume":"21","author":"L Maier-Hein","year":"2024","unstructured":"Maier-Hein L, Reinke A, Godau P, Tizabi MD, Buettner F, Christodoulou E, et al. Metrics reloaded: recommendations for image analysis validation. Nat Methods. 2024;21:195\u2013212. https:\/\/doi.org\/10.1038\/s41592-023-02151-z.","journal-title":"Nat Methods"},{"key":"7677_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-020-00173-2","volume":"4","author":"J Hofmanninger","year":"2020","unstructured":"Hofmanninger J, Prayer F, Pan J, Rohrich S, Prosch H, Langs G. Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur Radiol Exp. 2020;4:50. https:\/\/doi.org\/10.1186\/s41747-020-00173-2.","journal-title":"Eur Radiol Exp"},{"key":"7677_CR27","doi-asserted-by":"publisher","first-page":"643","DOI":"10.2967\/jnumed.123.267048","volume":"65","author":"KH Leung","year":"2024","unstructured":"Leung KH, Rowe SP, Sadaghiani MS, Leal JP, Mena E, Choyke PL, et al. Deep semisupervised transfer learning for fully automated whole-body tumor quantification and prognosis of cancer on PET\/CT. J Nucl Med. 2024;65:643\u201350. https:\/\/doi.org\/10.2967\/jnumed.123.267048.","journal-title":"J Nucl Med"},{"key":"7677_CR28","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1038\/s42256-025-01024-8","volume":"7","author":"T Chakraborti","year":"2025","unstructured":"Chakraborti T, Banerji CRS, Marandon A, Hellon V, Mitra R, Lehmann B, et al. Personalized uncertainty quantification in artificial intelligence. Nat Mach Intell. 2025;7:522\u201330. https:\/\/doi.org\/10.1038\/s42256-025-01024-8.","journal-title":"Nat Mach Intell"},{"key":"7677_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102830","volume":"150","author":"B Lambert","year":"2024","unstructured":"Lambert B, Forbes F, Doyle S, Dehaene H, Dojat M. Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis. Artif Intell Med. 2024;150:102830. https:\/\/doi.org\/10.1016\/j.artmed.2024.102830.","journal-title":"Artif Intell Med"}],"container-title":["European Journal of Nuclear Medicine and Molecular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-025-07677-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00259-025-07677-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-025-07677-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T01:25:58Z","timestamp":1774401958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00259-025-07677-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"references-count":29,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["7677"],"URL":"https:\/\/doi.org\/10.1007\/s00259-025-07677-2","relation":{},"ISSN":["1619-7070","1619-7089"],"issn-type":[{"value":"1619-7070","type":"print"},{"value":"1619-7089","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"14 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 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 was conducted in accordance with the principles of the Declaration of Helsinki. Ethical approval was obtained from the Ethics Committee of LMU University Hospital (approval no. 22\u20130416, June 2022). The requirement for informed consent was waived owing to the retrospective design.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"RAW reports speaker honoraria from Novartis\/AAA and PentixaPharm, reports advisory board work for Novartis\/AAA and Bayer. All other authors declare that they have no relevant competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}