{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:08:45Z","timestamp":1789380525377,"version":"build-2803163510"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T00:00:00Z","timestamp":1778889600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["101034290"],"award-info":[{"award-number":["101034290"]}],"id":[{"id":"10.13039\/100010665","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>Radiogenomics aims to non-invasively predict tumour genotypes from imaging, but most studies assume molecular homogeneity by assigning a single biopsy-derived label to all lesions within a patient. This approach risks substantial label noise given well-documented interlesional heterogeneity. We investigated whether anchoring training to biopsy-confirmed lesions improves radiogenomic model performance and generalisability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively analysed 1646 patients (11473 segmented lesions) with contrast-enhanced CT and EGFR mutation status from next-generation sequencing at the Netherlands Cancer Institute, alongside an external NSCLC radiogenomics cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009158). All visible lesions were segmented, and the exact biopsy site was matched to its segmentation. Radiomic features were extracted, and machine learning models were trained with three lesion selection strategies: all lesions, non-biopsied lesions only, and biopsy-confirmed lesions only. To disentangle label quality from sample size, we created size-matched variants (one lesion per patient) for all-lesion and non-biopsied strategies.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All models achieved significant discrimination of EGFR status on internal validation (AUC\u2009=\u20090.62\u20130.68). However, performance of the all-lesion and non-biopsied models declined on external validation (AUC\u2009=\u20090.55\u20130.63), while the biopsy-anchored model maintained stable performance (AUC\u2009=\u20090.62), despite having only 1\/10th of the training sample size. When training sets were size-matched, the biopsy-anchored approach significantly outperformed a model trained on all available lesions on external validation (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.037).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Radiogenomic models trained on biopsy-confirmed lesions outperform conventional all-lesion strategies in external validation, despite using an order of magnitude fewer samples. Prioritising lesion-level label fidelity can mitigate heterogeneity-driven noise, enhancing robustness and clinical translation of imaging-based genomic prediction.<\/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>Does assigning biopsy-derived molecular labels to all lesions introduce heterogeneity-driven label noise that reduces the generalisability of radiogenomic models?<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Models trained exclusively on biopsy-confirmed lesions demonstrated superior external generalisability compared with all-lesion approaches, despite being trained on substantially fewer samples.<\/jats:italic>\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Biopsy-anchored radiogenomics improves the reliability of non-invasive mutation prediction by accounting for tumour heterogeneity, potentially supporting clinical decision-making when tissue sampling is limited or molecular results are discordant across lesions.<\/jats:italic>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-026-12601-9","type":"journal-article","created":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T07:18:33Z","timestamp":1778915913000},"page":"7473-7489","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quality over quantity: biopsy-anchored CT radiogenomics models outperform all-lesion training in a multi-tumour cohort despite a smaller sample size"],"prefix":"10.1007","volume":"36","author":[{"given":"Diana Ivonne","family":"Rodr\u00edguez S\u00e1nchez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Middelkoop","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thera","family":"Vanneste","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Maxouri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Ursprung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sajjad","family":"Rostami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nino","family":"Bogveradze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kalina","family":"Chupetlovska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca","family":"Castagnoli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federica","family":"Landolfi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun Kyoung","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Delli Pizzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolo","family":"Gennaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Warissara","family":"Jutidamrongphan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liliana","family":"Petrychenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petur","family":"Snaebjornsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuhir","family":"Bodalal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8533-5090","authenticated-orcid":false,"given":"Regina","family":"Beets-Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,16]]},"reference":[{"key":"12601_CR1","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.3390\/cancers14061384","volume":"14","author":"P Gilson","year":"2022","unstructured":"Gilson P, Merlin J-L, Harl\u00e9 A (2022) Deciphering tumour heterogeneity: from tissue to liquid biopsy. Cancers (Basel) 14:1384. https:\/\/doi.org\/10.3390\/cancers14061384","journal-title":"Cancers (Basel)"},{"key":"12601_CR2","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/nrclinonc.2015.175","volume":"13","author":"MW Schmitt","year":"2015","unstructured":"Schmitt MW, Loeb LA, Salk JJ (2015) The influence of subclonal resistance mutations on targeted cancer therapy. Nat Rev Clin Oncol 13:335. https:\/\/doi.org\/10.1038\/nrclinonc.2015.175","journal-title":"Nat Rev Clin Oncol"},{"key":"12601_CR3","doi-asserted-by":"publisher","unstructured":"Rodr\u00edguez S\u00e1nchez DI, \u00d6zt\u00fcrk SA, Maxouri O et al (2026) Interlesional heterogeneity of EGFR mutations: a systematic review and meta-analysis. Mol Diagn Ther. https:\/\/doi.org\/10.1007\/s40291-026-00829-6","DOI":"10.1007\/s40291-026-00829-6"},{"key":"12601_CR4","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1038\/nrclinonc.2017.166","volume":"15","author":"I Dagogo-Jack","year":"2017","unstructured":"Dagogo-Jack I, Shaw AT (2017) Tumour heterogeneity and resistance to cancer therapies. Nat Rev Clin Oncol 15:81\u201394. https:\/\/doi.org\/10.1038\/nrclinonc.2017.166","journal-title":"Nat Rev Clin Oncol"},{"key":"12601_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms5006","volume":"5","author":"HJWL Aerts","year":"2014","unstructured":"Aerts HJWL, Velazquez ER, Leijenaar RTH et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:1\u20139. https:\/\/doi.org\/10.1038\/ncomms5006","journal-title":"Nat Commun"},{"key":"12601_CR6","doi-asserted-by":"publisher","unstructured":"Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are Data. Radiology 278. https:\/\/doi.org\/10.1148\/radiol.2015151169","DOI":"10.1148\/radiol.2015151169"},{"key":"12601_CR7","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.7150\/thno.30309","volume":"9","author":"Z Liu","year":"2019","unstructured":"Liu Z, Wang S, Dong D et al (2019) The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges. Theranostics 9:1303. https:\/\/doi.org\/10.7150\/thno.30309","journal-title":"Theranostics"},{"key":"12601_CR8","doi-asserted-by":"publisher","unstructured":"Sun R, Limkin EJ, Vakalopoulou M et al (2018) A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. The Lancet Oncology 19:1180\u20131191. https:\/\/doi.org\/10.1016\/S1470-2045(18)30413-3","DOI":"10.1016\/S1470-2045(18)30413-3"},{"key":"12601_CR9","doi-asserted-by":"publisher","unstructured":"Ferro A, Bottosso M, Dieci MV et al (2024) Clinical applications of radiomics and deep learning in breast and lung cancer: A narrative literature review on current evidence and future perspectives. Crit Rev Oncol Hematol 203:104479. https:\/\/doi.org\/10.1016\/j.critrevonc.2024.104479","DOI":"10.1016\/j.critrevonc.2024.104479"},{"key":"12601_CR10","doi-asserted-by":"publisher","unstructured":"Cui Y, Zhang J, Li Z et al (2022) A CT-based deep learning radiomics nomogram for predicting the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer: a multicenter cohort study. EClinicalMedicine 46. https:\/\/doi.org\/10.1016\/j.eclinm.2022.101348","DOI":"10.1016\/j.eclinm.2022.101348"},{"key":"12601_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12880-025-01759-1","volume":"25","author":"X Huang","year":"2025","unstructured":"Huang X, Huang X, Wang K et al (2025) 2.5D deep learning radiomics and clinical data for predicting occult lymph node metastasis in lung adenocarcinoma. BMC Med Imaging 25:1\u201317. https:\/\/doi.org\/10.1186\/s12880-025-01759-1","journal-title":"BMC Med Imaging"},{"key":"12601_CR12","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1007\/s00261-022-03534-0","volume":"47","author":"EK Hong","year":"2022","unstructured":"Hong EK, Bodalal Z, Landolfi F et al (2022) Identifying high-risk colon cancer on CT an a radiomics signature improve radiologist\u2019s performance for T staging? Abdom Radiol (NY) 47:2739\u20132746. https:\/\/doi.org\/10.1007\/s00261-022-03534-0","journal-title":"Abdom Radiol (NY)"},{"key":"12601_CR13","doi-asserted-by":"publisher","first-page":"100028","DOI":"10.1016\/j.iotech.2021.100028","volume":"9","author":"Z Bodalal","year":"2021","unstructured":"Bodalal Z, Wamelink I, Trebeschi S, Beets-Tan RGH (2021) Radiomics in immuno-oncology. Immunooncol Technol 9:100028. https:\/\/doi.org\/10.1016\/j.iotech.2021.100028","journal-title":"Immunooncol Technol"},{"key":"12601_CR14","doi-asserted-by":"publisher","unstructured":"Lo Gullo R, Daimiel I, Morris EA, Pinker K (2020) Combining molecular and imaging metrics in cancer: radiogenomics. Insights Imaging 11. https:\/\/doi.org\/10.1186\/s13244-019-0795-6","DOI":"10.1186\/s13244-019-0795-6"},{"key":"12601_CR15","doi-asserted-by":"publisher","unstructured":"Bodalal Z, Trebeschi S, Nguyen-Kim TDL et al (2019) Radiogenomics: bridging imaging and genomics. Abdom Radiol (NY) 44:1960\u20131984. https:\/\/doi.org\/10.1007\/s00261-019-02028-w","DOI":"10.1007\/s00261-019-02028-w"},{"key":"12601_CR16","doi-asserted-by":"publisher","first-page":"112738","DOI":"10.1016\/j.ejrad.2026.112738","volume":"198","author":"DI Rodr\u00edguez S\u00e1nchez","year":"2026","unstructured":"Rodr\u00edguez S\u00e1nchez DI, Vanneste T, Middelkoop J et al (2026) Concurrent driver mutations induce distinct tumour morphologies on radiological imaging. Eur J Radio 198:112738. https:\/\/doi.org\/10.1016\/j.ejrad.2026.112738","journal-title":"Eur J Radio"},{"key":"12601_CR17","doi-asserted-by":"publisher","unstructured":"Gow CH, Chang YL, Hsu YC et al (2009) Comparison of epidermal growth factor receptor mutations between primary and corresponding metastatic tumors in tyrosine kinase inhibitor-naive non-small-cell lung cancer. Ann Oncol 20. https:\/\/doi.org\/10.1093\/annonc\/mdn679","DOI":"10.1093\/annonc\/mdn679"},{"key":"12601_CR18","doi-asserted-by":"publisher","unstructured":"Demircio\u011flu A (2025) Reproducibility and interpretability in radiomics: a critical assessment. Diagn Interv Radiol. https:\/\/doi.org\/10.4274\/dir.2024.242719","DOI":"10.4274\/dir.2024.242719"},{"key":"12601_CR19","unstructured":"Bakr S, Gevaert O, Echegaray S et al (2017) Data for NSCLC radiogenomics collection. The Cancer Imaging Archive"},{"key":"12601_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.202","volume":"5","author":"S Bakr","year":"2018","unstructured":"Bakr S, Gevaert O, Echegaray S et al (2018) A radiogenomic dataset of non-small cell lung cancer. Sci Data 5:180202. https:\/\/doi.org\/10.1038\/sdata.2018.202","journal-title":"Sci Data"},{"key":"12601_CR21","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13244-023-01415-8","volume":"14","author":"B Kocak","year":"2023","unstructured":"Kocak B, Baessler B, Bakas S et al (2023) CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII. Insights Imaging 14:75. https:\/\/doi.org\/10.1186\/s13244-023-01415-8","journal-title":"Insights Imaging"},{"key":"12601_CR22","unstructured":"Pyradiomics developers (2025) Welcome to pyradiomics documentation!\u2014pyradiomics v3.1.0rc2.post5+g6a761c4 documentation. https:\/\/pyradiomics.readthedocs.io\/en\/latest\/. Accessed 24 Jul 2025"},{"key":"12601_CR23","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1148\/radiol.2020191145","volume":"295","author":"A Zwanenburg","year":"2020","unstructured":"Zwanenburg A, Valli\u00e8res M, Abdalah MA et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328\u2013338. https:\/\/doi.org\/10.1148\/radiol.2020191145","journal-title":"Radiology"},{"key":"12601_CR24","doi-asserted-by":"publisher","first-page":"369","DOI":"10.2967\/jnumed.110.082404","volume":"52","author":"F Tixier","year":"2011","unstructured":"Tixier F, Le Rest CC, Hatt M et al (2011) Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med 52:369\u2013378. https:\/\/doi.org\/10.2967\/jnumed.110.082404","journal-title":"J Nucl Med"},{"key":"12601_CR25","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","volume":"77","author":"JJM van Griethuysen","year":"2017","unstructured":"van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104\u2013e107. https:\/\/doi.org\/10.1158\/0008-5472.CAN-17-0339","journal-title":"Cancer Res"},{"key":"12601_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2018.11.008","volume":"52","author":"V Bol\u00f3n-Canedo","year":"2019","unstructured":"Bol\u00f3n-Canedo V, Alonso-Betanzos A (2019) Ensembles for feature selection: a review and future trends. Inf Fusion 52:1\u201312. https:\/\/doi.org\/10.1016\/j.inffus.2018.11.008","journal-title":"Inf Fusion"},{"key":"12601_CR27","doi-asserted-by":"publisher","first-page":"5951","DOI":"10.1007\/s00521-019-04082-3","volume":"32","author":"B Pes","year":"2020","unstructured":"Pes B (2020) Ensemble feature selection for high-dimensional data: a stability analysis across multiple domains. Neural Comput Appl 32:5951\u20135973. https:\/\/doi.org\/10.1007\/s00521-019-04082-3","journal-title":"Neural Comput Appl"},{"key":"12601_CR28","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1186\/s13244-023-01474-x","volume":"14","author":"Z Bodalal","year":"2023","unstructured":"Bodalal Z, Bogveradze N, Ter Beek LC et al (2023) Radiomic signatures from T2W and DWI MRI are predictive of tumour hypoxia in colorectal liver metastases. Insights Imaging 14:133. https:\/\/doi.org\/10.1186\/s13244-023-01474-x","journal-title":"Insights Imaging"},{"key":"12601_CR29","doi-asserted-by":"publisher","first-page":"108389","DOI":"10.1016\/j.compbiomed.2024.108389","volume":"174","author":"M Ahmadian","year":"2024","unstructured":"Ahmadian M, Bodalal Z, van der Hulst HJ et al (2024) Overcoming data scarcity in radiomics\/radiogenomics using synthetic radiomic features. Comput Biol Med 174:108389. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.108389","journal-title":"Comput Biol Med"},{"key":"12601_CR30","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s41747-024-00484-8","volume":"8","author":"Z Bodalal","year":"2024","unstructured":"Bodalal Z, Hong EK, Trebeschi S et al (2024) Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study. Eur Radio Exp 8:98. https:\/\/doi.org\/10.1186\/s41747-024-00484-8","journal-title":"Eur Radio Exp"},{"key":"12601_CR31","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1093\/bioinformatics\/btz470","volume":"36","author":"TT Le","year":"2020","unstructured":"Le TT, Fu W, Moore JH (2020) Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics 36:250\u2013256. https:\/\/doi.org\/10.1093\/bioinformatics\/btz470","journal-title":"Bioinformatics"},{"key":"12601_CR32","doi-asserted-by":"publisher","unstructured":"Olson RS, Urbanowicz RJ, Andrews PC, Lavender NA, Kidd LC, Moore JH (2016) In: Squillero G, Burelli P (eds) Automating biomedical data science through tree-based pipeline optimization. Applications of Evolutionary Computation. EvoApplications 2016, Proceedings, Part I. Cham: Springer, p. 123\u2013137. https:\/\/doi.org\/10.1007\/978-3-319-31204-0_9","DOI":"10.1007\/978-3-319-31204-0_9"},{"key":"12601_CR33","doi-asserted-by":"publisher","unstructured":"Olson RS, Bartley N, Urbanowicz RJ, Moore JH (2016) Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science. In Proceedings of the Genetic and Evolutionary Computation Conference 2016 (GECCO \u201916). ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2908812.2908918","DOI":"10.1145\/2908812.2908918"},{"key":"12601_CR34","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29\u201336. https:\/\/doi.org\/10.1148\/radiology.143.1.7063747","journal-title":"Radiology"},{"key":"12601_CR35","doi-asserted-by":"publisher","unstructured":"Liu Y, Kim J, Balagurunathan Y et al (2016) Radiomic features are associated with EGFR mutation status in lung adenocarcinomas. Clin Lung Cancer 17. https:\/\/doi.org\/10.1016\/j.cllc.2016.02.001","DOI":"10.1016\/j.cllc.2016.02.001"},{"key":"12601_CR36","doi-asserted-by":"publisher","unstructured":"He R, Yang X, Li T et al (2022) A machine learning-based predictive model of epidermal growth factor mutations in lung adenocarcinomas. Cancers (Basel) 14:4664. https:\/\/doi.org\/10.3390\/cancers14194664","DOI":"10.3390\/cancers14194664"},{"key":"12601_CR37","doi-asserted-by":"publisher","unstructured":"Felfli M, Liu Y, Zerka F et al (2023) Systematic review, meta-analysis and radiomics quality score assessment of CT radiomics-based models predicting tumor EGFR mutation status in patients with non-small-cell lung cancer. Int J Mol Sci 24. https:\/\/doi.org\/10.3390\/ijms241411433","DOI":"10.3390\/ijms241411433"},{"key":"12601_CR38","doi-asserted-by":"publisher","unstructured":"Lee CC, Soon YY, Tan CL et al (2019) Discordance of epidermal growth factor receptor mutation between primary lung tumor and paired distant metastases in non-small cell lung cancer: a systematic review and meta-analysis. PLoS One 14. https:\/\/doi.org\/10.1371\/journal.pone.0218414","DOI":"10.1371\/journal.pone.0218414"},{"key":"12601_CR39","doi-asserted-by":"publisher","unstructured":"Han HS, Eom DW, Kim JH et al (2011) EGFR mutation status in primary lung adenocarcinomas and corresponding metastatic lesions: discordance in pleural metastases. Clin Lung Cancer 12. https:\/\/doi.org\/10.1016\/j.cllc.2011.02.006","DOI":"10.1016\/j.cllc.2011.02.006"},{"key":"12601_CR40","doi-asserted-by":"publisher","first-page":"137","DOI":"10.14791\/btrt.2019.7.e44","volume":"7","author":"K-M Kim","year":"2019","unstructured":"Kim K-M, Lee S-H, Kim S-M et al (2019) Discordance of epidermal growth factor receptor mutation between brain metastasis and primary non-small cell lung cancer. Brain Tumor Res Treat 7:137. https:\/\/doi.org\/10.14791\/btrt.2019.7.e44","journal-title":"Brain Tumor Res Treat"},{"key":"12601_CR41","unstructured":"Firdoussi AE, Seddik MEA (2024) High-dimensional learning with noisy labels. arXiv. https:\/\/arxiv.org\/abs\/2405.14088"},{"key":"12601_CR42","doi-asserted-by":"publisher","unstructured":"Quellec G, Cazuguel G, Cochener B, Lamard M (2017) Multiple-instance learning for medical image and video analysis. IEE Reviews in Biomedical Engineering. https:\/\/doi.org\/10.1109\/RBME.2017.2651164. Accessed 5 Oct 2025","DOI":"10.1109\/RBME.2017.2651164"},{"key":"12601_CR43","doi-asserted-by":"publisher","unstructured":"Shi J, Zhang K, Guo C, Yang Y, Xu Y, Wu J (2024) A survey of label-noise deep learning for medical image analysis. Med Image Anal 95:103166. https:\/\/doi.org\/10.1016\/j.media.2024.103166","DOI":"10.1016\/j.media.2024.103166"},{"key":"12601_CR44","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1093\/jamia\/ocae108","volume":"31","author":"Y Wei","year":"2024","unstructured":"Wei Y, Deng Y, Sun C et al (2024) Deep learning with noisy labels in medical prediction problems: a scoping review. J Am Med Inf Assoc 31:1596\u20131607. https:\/\/doi.org\/10.1093\/jamia\/ocae108","journal-title":"J Am Med Inf Assoc"},{"key":"12601_CR45","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","volume":"14","author":"P Lambin","year":"2017","unstructured":"Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749\u2013762. https:\/\/doi.org\/10.1038\/nrclinonc.2017.141","journal-title":"Nat Rev Clin Oncol"},{"key":"12601_CR46","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.3348\/kjr.2018.0070","volume":"20","author":"JE Park","year":"2019","unstructured":"Park JE, Park SY, Kim HJ, Kim HS (2019) Reproducibility and generalizability in radiomics modeling: possible strategies in radiologic and statistical perspectives. Korean J Radiol 20:1124. https:\/\/doi.org\/10.3348\/kjr.2018.0070","journal-title":"Korean J Radiol"},{"key":"12601_CR47","doi-asserted-by":"publisher","first-page":"5985","DOI":"10.3390\/cancers13235985","volume":"13","author":"M Hershman","year":"2021","unstructured":"Hershman M, Yousefi B, Serletti L et al (2021) Impact of interobserver variability in manual segmentation of Non-Small Cell Lung Cancer (NSCLC) applying low-rank radiomic representation on computed tomography. Cancers (Basel) 13:5985. https:\/\/doi.org\/10.3390\/cancers13235985","journal-title":"Cancers (Basel)"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12601-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-026-12601-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12601-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:53:46Z","timestamp":1789379626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-026-12601-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,16]]},"references-count":47,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["12601"],"URL":"https:\/\/doi.org\/10.1007\/s00330-026-12601-9","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,16]]},"assertion":[{"value":"30 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The scientific guarantor of this publication is Prof. Regina Beets-Tan.","order":1,"name":"Ethics","label":"Guarantor","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Stephan Ursprung is a member of the\n                      European Radiology\n                      Editorial Board, and as such, they have not participated in the review or selection processes for this article. Zuhir Bodalal is a member of the\n                      European Radiology\n                      Editorial Board, and as such, they have not participated in the review or selection processes for this article.","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"One of the authors has significant statistical expertise.","order":3,"name":"Ethics","label":"Statistics and biometry","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"NA.","order":4,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Ethical approval was obtained from the institutional review board (IRBd19-147) of the NKI. All data collection and analysis were conducted in accordance with institutional policies and applicable regulations.","order":5,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"NA.","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"}}]}}