{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T19:06:48Z","timestamp":1792868808653,"version":"4.5.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Dokuz Eyl\u00fcl University","id":[{"id":"https:\/\/ror.org\/00dbd8b73","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neuroradiology"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Molecular subtyping guides diagnosis and targeted therapy for gliomas. Although MRI\u2014the current imaging standard\u2014can be time-consuming and is sometimes contraindicated, computed tomography (CT) is faster, more widely available, and often preferable in emergency and resource-limited settings. We evaluated whether CT-based radiogenomic signatures combined with machine learning could accurately predict clinically relevant glioma molecular markers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective study, we characterised non-contrast CT (NCCT) scans from 197 adults with histologically confirmed gliomas. Models were developed to predict mutations in four molecular markers: ATRX (\n                      <jats:italic>n<\/jats:italic>\n                      =81), EGFR (\n                      <jats:italic>n<\/jats:italic>\n                      =17), TP53 (\n                      <jats:italic>n<\/jats:italic>\n                      =71), and IDH (\n                      <jats:italic>n<\/jats:italic>\n                      =183). We extracted 208 quantitative radiomic features and added basic demographic variables. Feature selection used LASSO-RFE and Gradient Boosting\u2013RFE with cross-validation. Six classical machine-learning classifiers and deep-learning approaches \u2014 including custom fully connected neural networks (FCNN) and TabNet \u2014 were trained and compared using ROC\u2013AUC as the primary performance metric.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Deep-learning methods outperformed conventional classifiers for all targets. TabNet achieved ROC\u2013AUCs of 0.900 (95% CI: 0.717\u20130.989; ATRX), 0.955 (95% CI: 0.661\u20130.978; TP53), and 0.917 (95% CI: 0.858\u20130.975; EGFR). A custom FCNN obtained a ROC\u2013AUC of 0.971 (95% CI: 0.876\u20130.995) for IDH. Cross-validation coefficients of variation were 2.0% for ATRX and 3.0% for TP53 and EGFR, and 16.0% for IDH. Deep-learning approaches yielded statistically significant improvements over conventional methods (\n                      <jats:italic>p<\/jats:italic>\n                      -values ranging from &lt;0.05 to &lt;0.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>NCCT-based analytical methods were able to predict clinically relevant genetic mutations in gliomas and demonstrated performance comparable to established techniques. These findings suggest that CT may serve as a practical option for molecular profiling in urgent or resource-limited settings. Nonetheless, external validation is necessary prior to clinical translation. The EGFR findings, arising from a small EGFR-tested subgroup (n = 17), remain preliminary; the observed performance may not reflect generalisable accuracy, and independent validation in larger cohorts is required.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00234-026-04043-3","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T02:02:58Z","timestamp":1780538578000},"page":"2859-2875","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CT-based deep learning radiogenomics for predicting key glioma genotypes (IDH, ATRX, EGFR, TP53)"],"prefix":"10.1007","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1601-7424","authenticated-orcid":false,"given":"Zohal Alnour Ahmed","family":"Emam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0463-0945","authenticated-orcid":false,"given":"Emel","family":"Ada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6535-8845","authenticated-orcid":false,"given":"Bur\u00e7in","family":"Pehlivano\u011flu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1997-8861","authenticated-orcid":false,"given":"Berrin","family":"\u00c7avu\u015fo\u011flu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1071-4405","authenticated-orcid":false,"given":"Kadir","family":"Akg\u00fcng\u00f6r","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8445-0388","authenticated-orcid":false,"given":"M. Alper","family":"Selver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"issue":"8","key":"4043_CR1","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1093\/neuonc\/noab106","volume":"23","author":"DN Louis","year":"2021","unstructured":"Louis DN, Perry A, Wesseling P et al (2021) The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro Oncol 23(8):1231\u20131251. https:\/\/doi.org\/10.1093\/neuonc\/noab106","journal-title":"Neuro Oncol"},{"issue":"12 Suppl 2","key":"4043_CR2","doi-asserted-by":"publisher","first-page":"iv1","DOI":"10.1093\/neuonc\/noad149","volume":"25","author":"QT Ostrom","year":"2023","unstructured":"Ostrom QT, Price M, Neff C, Cioffi G, Waite KA, Kruchko C, Barnholtz-Sloan JS (2023) CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2016\u20132020. Neuro Oncol 25(12 Suppl 2):iv1\u2013iv99. https:\/\/doi.org\/10.1093\/neuonc\/noad149","journal-title":"Neuro Oncol"},{"issue":"6","key":"4043_CR3","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.3390\/biomedicines13061298","volume":"13","author":"P Rajakaruna","year":"2025","unstructured":"Rajakaruna P, Rios S, Elnahas H et al (2025) Molecular biomarkers of glioma: integrating radiogenomic dimensions. Biomedicines 13(6):1298. https:\/\/doi.org\/10.3390\/biomedicines13061298","journal-title":"Biomedicines"},{"issue":"7274","key":"4043_CR4","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1038\/nature08617","volume":"462","author":"L Dang","year":"2009","unstructured":"Dang L, White DW, Gross S et al (2009) Cancer-associated IDH1 mutations produce 2-hydroxyglutarate. Nature 462(7274):739\u2013744. https:\/\/doi.org\/10.1038\/nature08617","journal-title":"Nature"},{"issue":"9","key":"4043_CR5","doi-asserted-by":"publisher","first-page":"297","DOI":"10.3390\/cancers10090297","volume":"10","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Dube C, Gibert M et al (2018) The p53 pathway in glioblastoma. Cancers 10(9):297. https:\/\/doi.org\/10.3390\/cancers10090297","journal-title":"Cancers"},{"issue":"2","key":"4043_CR6","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/j.cell.2013.09.034","volume":"155","author":"CW Brennan","year":"2013","unstructured":"Brennan CW, Verhaak RG, McKenna A et al (2013) The somatic genomic landscape of glioblastoma. Cell 155(2):462\u2013477. https:\/\/doi.org\/10.1016\/j.cell.2013.09.034","journal-title":"Cell"},{"issue":"10","key":"4043_CR7","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1093\/neuonc\/noac105","volume":"24","author":"J Ding","year":"2022","unstructured":"Ding J, Li X, Khan S et al (2022) EGFR suppresses p53 function by promoting p53 binding to DNA-PKcs: a noncanonical regulatory axis in glioblastoma. Neuro Oncol 24(10):1712\u20131725. https:\/\/doi.org\/10.1093\/neuonc\/noac105","journal-title":"Neuro Oncol"},{"issue":"6041","key":"4043_CR8","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1126\/science.1207313","volume":"333","author":"CM Heaphy","year":"2011","unstructured":"Heaphy CM, de Wilde RF, Jiao Y et al (2011) Altered telomeres in tumors with ATRX and DAXX mutations. Science 333(6041):425. https:\/\/doi.org\/10.1126\/science.1207313","journal-title":"Science"},{"issue":"3","key":"4043_CR9","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1038\/s41571-020-00447-z","volume":"18","author":"M Weller","year":"2021","unstructured":"Weller M, van den Bent M, Preusser M et al (2021) EANO guidelines on the diagnosis and treatment of diffuse gliomas of adulthood. Nat Rev Clin Oncol 18(3):170\u2013186. https:\/\/doi.org\/10.1038\/s41571-020-00447-z","journal-title":"Nat Rev Clin Oncol"},{"issue":"3","key":"4043_CR10","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.surneu.2007.12.019","volume":"71","author":"MJ McGirt","year":"2009","unstructured":"McGirt MJ, Villavicencio AT, Bulsara KR, Friedman AH (2009) MRI-guided stereotactic biopsy in glioma diagnosis: concordance with resection specimens. Surg Neurol 71(3):280\u2013286. https:\/\/www.ncbi.nlm.nih.gov\/pubmed\/12748009","journal-title":"Surg Neurol"},{"key":"4043_CR11","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s41698-024-00789-2","volume":"9","author":"FJ Dorfner","year":"2025","unstructured":"Dorfner FJ, Patel JB, Kalpathy-Cramer J et al (2025) A review of deep learning for brain tumor analysis in MRI. NPJ Precis Oncol 9:2. https:\/\/doi.org\/10.1038\/s41698-024-00789-2","journal-title":"NPJ Precis Oncol"},{"issue":"8","key":"4043_CR12","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.44214","volume":"15","author":"M Ibrahim","year":"2023","unstructured":"Ibrahim M, Muhammad Q, Zamarud A et al (2023) Navigating Glioblastoma diagnosis and care: transformative pathway of artificial intelligence in integrative oncology. Cureus 15(8):e44214. https:\/\/doi.org\/10.7759\/cureus.44214","journal-title":"Cureus"},{"key":"4043_CR13","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11033-024-10051-4","volume":"52","author":"MR Patil","year":"2025","unstructured":"Patil MR, Bihari A (2025) Role of artificial intelligence in cancer detection using Protein p53: a review. Mol Biol Rep 52:46. https:\/\/doi.org\/10.1007\/s11033-024-10051-4","journal-title":"Mol Biol Rep"},{"key":"4043_CR14","doi-asserted-by":"publisher","first-page":"1493824","DOI":"10.3389\/fradi.2024.1493824","volume":"4","author":"A Rodriguez-Ruiz","year":"2024","unstructured":"Rodriguez-Ruiz A, Montagnon E, Sylvestre JA et al (2024) Predicting IDH and ATRX mutations in gliomas using radiomics: a meta-analysis. Front Radiol 4:1493824. https:\/\/doi.org\/10.3389\/fradi.2024.1493824","journal-title":"Front Radiol"},{"key":"4043_CR15","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1409760","volume":"14","author":"X Chen","year":"2024","unstructured":"Chen X, Lei J, Wang S, Zhang J, Gou L (2024) Diagnostic accuracy of a machine learning-based radiomics approach of MR in predicting IDH mutations in glioma patients: a systematic review and meta-analysis. Front Oncol 14:1409760. https:\/\/doi.org\/10.3389\/fonc.2024.1409760","journal-title":"Front Oncol"},{"key":"4043_CR16","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-025-01221-7","volume":"12","author":"J Liu","year":"2025","unstructured":"Liu J, Shen C, Jiang S et al (2025) Deep learning-based tumor segmentation and radiogenomic model for predicting EGFR amplification and assessing intratumoural heterogeneity in glioblastoma. J Big Data 12:168. https:\/\/doi.org\/10.1186\/s40537-025-01221-7","journal-title":"J Big Data"},{"issue":"7","key":"4043_CR17","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15070797","volume":"15","author":"S Farahani","year":"2025","unstructured":"Farahani S, Hejazi M, Moradizeyveh S, Di Ieva A, Fatemizadeh E, Liu S (2025) Diagnostic accuracy of deep learning models in predicting glioma molecular markers: a systematic review and meta-analysis. Diagnostics Basel 15(7):797. https:\/\/doi.org\/10.3390\/diagnostics15070797","journal-title":"Diagnostics Basel"},{"key":"4043_CR18","unstructured":"Ghadimi M, Thomas A (2025) Magnetic Resonance Imaging Contraindications. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; Available from: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK551669\/. Accessed 28 May 2025"},{"issue":"1","key":"4043_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-77789-6","volume":"14","author":"M Musigmann","year":"2024","unstructured":"Musigmann M, Bilgin M, Bilgin SS, Kr\u00e4hling H, Heindel W, Mannil M (2024) Completely non-invasive prediction of IDH mutation status based on preoperative native CT images. Sci Rep 14(1):26763. https:\/\/doi.org\/10.1038\/s41598-024-77789-6","journal-title":"Sci Rep"},{"key":"4043_CR20","doi-asserted-by":"publisher","first-page":"e2300439","DOI":"10.1200\/GO.23.00439","volume":"10","author":"OA Bamodu","year":"2024","unstructured":"Bamodu OA et al (2024) Cancer Care Disparities: Overcoming Barriers to Cancer Control in Low- and Middle-Income Countries. JCO Glob Oncol 10:e2300439. https:\/\/doi.org\/10.1200\/GO.23.00439","journal-title":"JCO Glob Oncol"},{"key":"4043_CR21","doi-asserted-by":"publisher","first-page":"e389322","DOI":"10.1200\/EDBK_389322","volume":"43","author":"AB Porter","year":"2023","unstructured":"Porter AB, Wen PY, Polley MC (2023) Molecular Profiling in Neuro-Oncology: Where We Are, Where We\u2019re Heading, and How We Ensure Everyone Can Come Along. Am Soc Clin Oncol Educ Book 43:e389322. https:\/\/doi.org\/10.1200\/EDBK_389322","journal-title":"Am Soc Clin Oncol Educ Book"},{"key":"4043_CR22","unstructured":"CancerDisparitiesProgressReport.org [Internet] Philadelphia: American Association for Cancer Research; 2024 [cited 2025 Feb 15]. Available from: http:\/\/www.CancerDisparitiesProgressReport.org\/"},{"key":"4043_CR23","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533\u2013536. https:\/\/doi.org\/10.1038\/323533a0","journal-title":"Nature"},{"key":"4043_CR24","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Feedforward networks. In: Deep learning. Cambridge (MA): MIT Press; pp. 164\u2013223. Available from: https:\/\/www.deeplearningbook.org\/contents\/mlp.html"},{"key":"4043_CR25","doi-asserted-by":"publisher","unstructured":"Arik SO, Pfister T (2021) TabNet: attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence. ;35(8):6679\u20136687. https:\/\/doi.org\/10.1609\/aaai.v35i8.16826","DOI":"10.1609\/aaai.v35i8.16826"},{"issue":"7","key":"4043_CR26","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-048008","volume":"11","author":"GS Collins","year":"2021","unstructured":"Collins GS, Dhiman P, Andaur Navarro CL, Ma J, Hooft L, Reitsma JB, Logullo P, Beam AL, Peng L, Van Calster B, van Smeden M, Riley RD, Moons KG (2021) Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open 11(7):e048008. https:\/\/doi.org\/10.1136\/bmjopen-2020-048008","journal-title":"BMJ Open"},{"issue":"6","key":"4043_CR27","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1007\/s00401-016-1545-1","volume":"131","author":"DN Louis","year":"2016","unstructured":"Louis DN, Perry A, Reifenberger G, Von Deimling A, Figarella-Branger D, Cavenee WK, Ohgaki H, Wiestler OD, Kleihues P, Ellison DW (2016) The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Acta Neuropathol 131(6):803\u2013820. https:\/\/doi.org\/10.1007\/s00401-016-1545-1","journal-title":"Acta Neuropathol"},{"key":"4043_CR28","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1007\/s11548-013-0840-8","volume":"8","author":"M Nolden","year":"2013","unstructured":"Nolden M, Zelzer S, Seitel A et al (2013) The Medical Imaging Interaction Toolkit: challenges and advances. Int J Comput Assist Radiol Surg 8:607\u2013620. https:\/\/doi.org\/10.1007\/s11548-013-0840-8","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"4043_CR29","unstructured":"MathWorks (2024) Medical Imaging Toolbox [Computer software]. The MathWorks, Inc. https:\/\/www.mathworks.com\/products\/medical-imaging.html. Accessed 22 Jul 2024"},{"key":"4043_CR30","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321\u2013357. https:\/\/doi.org\/10.1613\/jair.953","journal-title":"J Artif Intell Res"},{"key":"4043_CR31","doi-asserted-by":"publisher","unstructured":"He H, Bai Y, Garcia EA, Li S, ADASYN (2008) Adaptive synthetic sampling approach for imbalanced learning. 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong pp. 1322\u20131328. https:\/\/doi.org\/10.1109\/IJCNN.2008.4633969","DOI":"10.1109\/IJCNN.2008.4633969"},{"issue":"11","key":"4043_CR32","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TSMC.1976.4309452","volume":"6","author":"I Tomek","year":"1976","unstructured":"Tomek I (1976) Two modifications of CNN. IEEE Trans Syst Man Cybern 6(11):769\u2013772. https:\/\/doi.org\/10.1109\/TSMC.1976.4309452","journal-title":"IEEE Trans Syst Man Cybern"},{"issue":"3","key":"4043_CR33","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1111\/j.1467-9868.2011.00771.x","volume":"73","author":"R Tibshirani","year":"2011","unstructured":"Tibshirani R (2011) Regression shrinkage and selection via the Lasso: a retrospective. J R Stat Soc B Stat Methodol 73(3):273\u2013282. https:\/\/doi.org\/10.1111\/j.1467-9868.2011.00771.x","journal-title":"J R Stat Soc B Stat Methodol"},{"key":"4043_CR34","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1162\/153244303322753616","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157\u20131182. https:\/\/doi.org\/10.1162\/153244303322753616","journal-title":"J Mach Learn Res"},{"key":"4043_CR35","doi-asserted-by":"publisher","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M, Optuna (2019) A next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. pp. 2623\u20132631. https:\/\/doi.org\/10.48550\/arXiv.1907.10902","DOI":"10.48550\/arXiv.1907.10902"},{"key":"4043_CR36","unstructured":"Bergstra J, Bardenet R, Bengio Y, K\u00e9gl B (2011) Algorithms for hyper-parameter optimization. Adv Neural Inf Process Syst 24:2546\u20132554. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2011\/file\/86e8f7ab32cfd12577bc2619bc635690-Paper.pdf"},{"issue":"1","key":"4043_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-7-91","volume":"7","author":"S Varma","year":"2006","unstructured":"Varma S, Simon R (2006) Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7(1):1\u20138. https:\/\/doi.org\/10.1186\/1471-2105-7-91","journal-title":"BMC Bioinformatics"},{"key":"4043_CR38","doi-asserted-by":"publisher","unstructured":"Little RJ, Rubin DB (2019) Statistical analysis with missing data. Wiley. https:\/\/doi.org\/10.1002\/9781119482260","DOI":"10.1002\/9781119482260"},{"key":"4043_CR39","doi-asserted-by":"crossref","unstructured":"Hastie T, Tibshirani R, Friedman J (2009) High-dimensional problems: p >> N. In: The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New York pp 649\u2013699. https:\/\/www.sas.upenn.edu\/~fdiebold\/NoHesitations\/BookAdvanced.pdf","DOI":"10.1007\/978-0-387-84858-7_18"},{"key":"4043_CR40","unstructured":"Cohen J (1988) Multiple regression and correlation analysis. In: Statistical power analysis for the behavioral sciences, 2nd edn. Lawrence Erlbaum Associates, Hillsdale, pp 407\u2013465. https:\/\/utstat.toronto.edu\/~brunner\/oldclass\/378f16\/readings\/CohenPower.pdf"},{"issue":"2","key":"4043_CR41","first-page":"1137","volume":"14","author":"R Kohavi","year":"1995","unstructured":"Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. IJCAI 14(2):1137\u20131145. https:\/\/www.ijcai.org\/Proceedings\/95-2\/Papers\/016.pdf","journal-title":"IJCAI"},{"key":"4043_CR42","doi-asserted-by":"crossref","unstructured":"Efron B, Tibshirani RJ (1993) An introduction to the bootstrap. Chapman and Hall\/CRC. https:\/\/www.hms.harvard.edu\/bss\/neuro\/bornlab\/nb204\/statistics\/bootstrap.pdf","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"4043_CR43","doi-asserted-by":"publisher","unstructured":"Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. 2017 IEEE Symposium on Security and Privacy 39\u201357. https:\/\/doi.org\/10.48550\/arXiv.1608.04644","DOI":"10.48550\/arXiv.1608.04644"},{"key":"4043_CR44","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1080\/01621459.1987.10478410","volume":"82","author":"B Efron","year":"1987","unstructured":"Efron B (1987) Better bootstrap confidence intervals. J Am Stat Assoc 82:171\u2013185. https:\/\/doi.org\/10.1080\/01621459.1987.10478410","journal-title":"J Am Stat Assoc"},{"key":"4043_CR45","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1214\/ss\/1032280214","volume":"11","author":"TJ DiCiccio","year":"1996","unstructured":"DiCiccio TJ, Efron B (1996) Bootstrap confidence intervals. Stat Sci 11:189\u2013228. https:\/\/doi.org\/10.1214\/ss\/1032280214","journal-title":"Stat Sci"},{"key":"4043_CR46","doi-asserted-by":"publisher","unstructured":"Nadeau C, Bengio Y (2003) Inference for the generalization error. Mach Learn 52:239\u2013281. https:\/\/doi.org\/10.1023\/A:1024068626366\u00a0","DOI":"10.1023\/A:1024068626366"},{"key":"4043_CR47","unstructured":"Python Software Foundation (2024) Python Language Reference (Version 3.12). Available from: https:\/\/docs.python.org\/3.12\/reference\/. Accessed 23 Aug 2024"},{"issue":"3","key":"4043_CR48","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3):837\u2013845. https:\/\/doi.org\/10.2307\/2531595","journal-title":"Biometrics"},{"key":"4043_CR49","doi-asserted-by":"publisher","unstructured":"Rainio O, Teuho J, Kl\u00e9n R (2024) Evaluation metrics and statistical tests for machine learning. Sci Rep 14:6086. https:\/\/doi.org\/10.1038\/s41598-024-56706-x","DOI":"10.1038\/s41598-024-56706-x"},{"key":"4043_CR50","doi-asserted-by":"publisher","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825\u20132830. https:\/\/doi.org\/10.48550\/arXiv.1201.0490","DOI":"10.48550\/arXiv.1201.0490"},{"key":"4043_CR51","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189\u20131232. https:\/\/doi.org\/10.1214\/aos\/1013203451","journal-title":"Ann Stat"},{"key":"4043_CR52","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"4043_CR53","doi-asserted-by":"publisher","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Man\u00e9 D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Vi\u00e9gas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2016) Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467. https:\/\/doi.org\/10.48550\/arXiv.1603.04467","DOI":"10.48550\/arXiv.1603.04467"},{"key":"4043_CR54","doi-asserted-by":"publisher","first-page":"8026","DOI":"10.48550\/arXiv.1912.01703","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Kopf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) PyTorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32:8026\u20138037. https:\/\/doi.org\/10.48550\/arXiv.1912.01703","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"4043_CR55","doi-asserted-by":"publisher","first-page":"261","DOI":"10.48550\/arXiv.1907.10121","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, Burovski E, Peterson P, Weckesser W, Bright J, van der Walt SJ, Brett M, Wilson J, Millman KJ, Mayorov N, Nelson AR, Jones E, Kern R, Larson E, Carey CJ, Polat \u0130, Feng Y, Moore EW, VanderPlas J, Laxalde D, Perktold J, Cimrman R, Henriksen I, Quintero EA, Harris CR, Archibald AM, Ribeiro AH, Pedregosa F, van Mulbregt P (2020) SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17(3):261\u2013272 https:\/\/doi.org\/10.48550\/arXiv.1907.10121","journal-title":"Nat Methods"},{"issue":"3","key":"4043_CR56","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter JD, Matplotlib (2007) A 2D graphics environment. Comput Sci Eng 9(3):90\u201395. https:\/\/doi.org\/10.1109\/MCSE.2007.55","journal-title":"Comput Sci Eng"},{"issue":"60","key":"4043_CR57","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","volume":"6","author":"ML Waskom","year":"2021","unstructured":"Waskom ML (2021) Seaborn: statistical data visualization. J Open Source Softw 6(60):3021. https:\/\/doi.org\/10.21105\/joss.03021","journal-title":"J Open Source Softw"}],"container-title":["Neuroradiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04043-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04043-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04043-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T18:02:54Z","timestamp":1792432974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04043-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":57,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["4043"],"URL":"https:\/\/doi.org\/10.1007\/s00234-026-04043-3","relation":{},"ISSN":["0028-3940","1432-1920"],"issn-type":[{"value":"0028-3940","type":"print"},{"value":"1432-1920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"assertion":[{"value":"22 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Ethical approval was granted by the Research Ethics Review Board of the Non-Interventional Ethics Committee at a tertiary-level academic hospital (approval reference number: 2021\/22\u201335) on 28 July 2021. The requirement for informed consent was waived due to the retrospective design of the study and the full anonymisation of all patient data prior to analysis.","order":1,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}