{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T02:26:21Z","timestamp":1793672781574,"version":"4.5.1"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T00:00:00Z","timestamp":1791849600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"publisher","award":["ANR-10-IAIHU-06"],"award-info":[{"award-number":["ANR-10-IAIHU-06"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"French National Research Agency","doi-asserted-by":"publisher","award":["ANR-23-IACL-0008"],"award-info":[{"award-number":["ANR-23-IACL-0008"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010449","name":"National Center for Tumor Diseases Heidelberg","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010449","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","award":["101136607"],"award-info":[{"award-number":["101136607"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101002198"],"award-info":[{"award-number":["101002198"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.media.2026.104349","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T16:00:11Z","timestamp":1791820811000},"page":"104349","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Performance uncertainty in medical image analysis: A large-scale investigation of confidence intervals"],"prefix":"10.1016","volume":"116","author":[{"given":"Pascaline","family":"Andr\u00e9","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Heitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelia","family":"Christodoulou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annika","family":"Reinke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carole H.","family":"Sudre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3005-4523","authenticated-orcid":false,"given":"Michela","family":"Antonelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0365-7265","authenticated-orcid":false,"given":"Patrick","family":"Godau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Jorge","family":"Cardoso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1777-0433","authenticated-orcid":false,"given":"Antoine","family":"Gilson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2866-4330","authenticated-orcid":false,"given":"Sophie","family":"Tezenas du Montcel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ga\u00ebl","family":"Varoquaux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4910-9368","authenticated-orcid":false,"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9836-654X","authenticated-orcid":false,"given":"Olivier","family":"Colliot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104349_b1","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: Techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.media.2026.104349_b2","series-title":"Encyclopedia of Research Design","article-title":"Jackknife","author":"Abdi","year":"2010"},{"key":"10.1016\/j.media.2026.104349_b3","series-title":"Introduction to concentration inequalities","author":"Abhishek","year":"2019"},{"key":"10.1016\/j.media.2026.104349_b4","first-page":"29304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","volume":"34","author":"Agarwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.media.2026.104349_b5","first-page":"119","article-title":"Approximate is better than \u201cexact\u201d for interval estimation of binomial proportions","volume":"52","author":"Agresti","year":"1998","journal-title":"Amer. Statist."},{"key":"10.1016\/j.media.2026.104349_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images","volume":"28","author":"Al-Dhabyani","year":"2020","journal-title":"Data Brief"},{"key":"10.1016\/j.media.2026.104349_b7","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"15","article-title":"Some hidden traps of confidence intervals in medical image segmentation: coverage issues","author":"Andr\u00e9","year":"2025"},{"issue":"4","key":"10.1016\/j.media.2026.104349_b8","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1561\/2200000101","article-title":"Conformal prediction: A gentle introduction","volume":"16","author":"Angelopoulos","year":"2023","journal-title":"Found. Trends\u00ae Mach. Learn."},{"issue":"1","key":"10.1016\/j.media.2026.104349_b9","doi-asserted-by":"crossref","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","article-title":"The medical segmentation decathlon","volume":"13","author":"Antonelli","year":"2022","journal-title":"Nat. Commun."},{"key":"10.1016\/j.media.2026.104349_b10","first-page":"16339","article-title":"Cross-validation confidence intervals for test error","volume":"33","author":"Bayle","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.media.2026.104349_b11","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"issue":"1","key":"10.1016\/j.media.2026.104349_b12","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1038\/s41597-020-00622-y","article-title":"HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy","volume":"7","author":"Borgli","year":"2020","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104349_b13","series-title":"Concentration Inequalities: A Nonasymptotic Theory of Independence","author":"Boucheron","year":"2013"},{"key":"10.1016\/j.media.2026.104349_b14","first-page":"747","article-title":"Accounting for variance in machine learning benchmarks","volume":"3","author":"Bouthillier","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"issue":"2","key":"10.1016\/j.media.2026.104349_b15","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1214\/ss\/1009213286","article-title":"Interval estimation for a binomial proportion","volume":"16","author":"Brown","year":"2001","journal-title":"Statist. Sci."},{"key":"10.1016\/j.media.2026.104349_b16","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1162\/tacl_a_00715","article-title":"Conformal prediction for natural language processing: A survey","volume":"12","author":"Campos","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.media.2026.104349_b17","series-title":"Monai: An open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b18","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1080\/02664763.2022.2118245","article-title":"Continuity corrected score confidence interval for the difference in proportions in paired data","volume":"51","author":"Chang","year":"2024","journal-title":"J. Appl. Stat."},{"key":"10.1016\/j.media.2026.104349_b19","doi-asserted-by":"crossref","first-page":"653","DOI":"10.2307\/3802084","article-title":"A comparison of confidence interval methods for habitat use-availability studies","author":"Cherry","year":"1996","journal-title":"J. Wildl. Manag."},{"key":"10.1016\/j.media.2026.104349_b20","series-title":"False promises in medical imaging ai? Assessing validity of outperformance claims","author":"Christodoulou","year":"2025"},{"key":"10.1016\/j.media.2026.104349_b21","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"124","article-title":"Confidence intervals uncovered: Are we ready for real-world medical imaging ai?","author":"Christodoulou","year":"2024"},{"issue":"4","key":"10.1016\/j.media.2026.104349_b22","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","article-title":"The use of confidence or fiducial limits illustrated in the case of the binomial","volume":"26","author":"Clopper","year":"1934","journal-title":"Biometrika"},{"key":"10.1016\/j.media.2026.104349_b23","series-title":"Mathematical Methods of Statistics","volume":"vol. 9","author":"Cram\u00e9r","year":"1999"},{"issue":"4","key":"10.1016\/j.media.2026.104349_b24","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1177\/0013164401614002","article-title":"A primer on the understanding, use, and calculation of confidence intervals that are based on central and noncentral distributions","volume":"61","author":"Cumming","year":"2001","journal-title":"Educ. Psychol. Meas."},{"issue":"1","key":"10.1016\/j.media.2026.104349_b25","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1007\/s10462-022-10178-5","article-title":"Valid prediction intervals for regression problems","volume":"56","author":"Dewolf","year":"2023","journal-title":"Artif. Intell. Rev."},{"issue":"7","key":"10.1016\/j.media.2026.104349_b26","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput."},{"key":"10.1016\/j.media.2026.104349_b27","doi-asserted-by":"crossref","first-page":"401","DOI":"10.2307\/2531060","article-title":"A comparison of confidence interval methods for the intraclass correlation coefficient","author":"Donner","year":"1986","journal-title":"Biometrics"},{"issue":"3","key":"10.1016\/j.media.2026.104349_b28","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1093\/biomet\/68.3.589","article-title":"Nonparametric estimates of standard error: the jackknife, the bootstrap and other methods","volume":"68","author":"Efron","year":"1981","journal-title":"Biometrika"},{"issue":"397","key":"10.1016\/j.media.2026.104349_b29","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1080\/01621459.1987.10478410","article-title":"Better bootstrap confidence intervals","volume":"82","author":"Efron","year":"1987","journal-title":"J. Amer. Statist. Assoc."},{"key":"10.1016\/j.media.2026.104349_b30","series-title":"Breakthroughs in Statistics: Methodology and Distribution","first-page":"569","article-title":"Bootstrap methods: another look at the jackknife","author":"Efron","year":"1992"},{"key":"10.1016\/j.media.2026.104349_b31","series-title":"Biomedical image analysis competitions: The state of current participation practice","author":"Eisenmann","year":"2022"},{"key":"10.1016\/j.media.2026.104349_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2025.103565","article-title":"Confidence intervals for performance estimates in 3D medical image segmentation","author":"El Jurdi","year":"2025","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104349_b33","series-title":"Crossing the validation crisis: Cross-validation reduces benchmarking variance surprisingly well","author":"Eve","year":"2026"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b34","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1002\/(SICI)1097-0258(20000115)19:1<61::AID-SIM297>3.0.CO;2-A","article-title":"The effect of random measurement error on receiver operating characteristic (ROC) curves","volume":"19","author":"Faraggi","year":"2000","journal-title":"Stat. Med."},{"key":"10.1016\/j.media.2026.104349_b35","series-title":"FDA-2024-D-4488: Artificial intelligence-enabled device software functions: Lifecycle management and marketing submission recommendations","author":"FDA","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b36","doi-asserted-by":"crossref","DOI":"10.1117\/1.JMI.6.1.014502","article-title":"In-vivo barrett\u2019s esophagus digital pathology stage classification through feature enhancement of confocal laser endomicroscopy","volume":"6","author":"Ghatwary","year":"2019","journal-title":"J. Med. Imaging"},{"key":"10.1016\/j.media.2026.104349_b37","series-title":"Beyond knowledge silos: Task fingerprinting for democratization of medical imaging ai","author":"Godau","year":"2024"},{"key":"10.1016\/j.media.2026.104349_b38","series-title":"The Bootstrap and Edgeworth Expansion","author":"Hall","year":"1992"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b39","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","article-title":"The meaning and use of the area under a receiver operating characteristic (ROC) curve","volume":"143","author":"Hanley","year":"1982","journal-title":"Radiology"},{"key":"10.1016\/j.media.2026.104349_b40","article-title":"A survey on uncertainty quantification methods for deep learning","author":"He","year":"2025","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"10.1016\/j.media.2026.104349_b41","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1080\/00031305.2015.1089789","article-title":"What teachers should know about the bootstrap: Resampling in the undergraduate statistics curriculum","volume":"69","author":"Hesterberg","year":"2015","journal-title":"Amer. Statist."},{"issue":"301","key":"10.1016\/j.media.2026.104349_b42","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","article-title":"Probability inequalities for sums of bounded random variables","volume":"58","author":"Hoeffding","year":"1963","journal-title":"J. Amer. Statist. Assoc."},{"key":"10.1016\/j.media.2026.104349_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103223","article-title":"A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods","volume":"97","author":"Huang","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104349_b44","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"590","article-title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","volume":"vol. 33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.media.2026.104349_b45","series-title":"The Theory of Probability","author":"Jeffreys","year":"1998"},{"key":"10.1016\/j.media.2026.104349_b46","series-title":"Cataract dataset","author":"jr2ngb","year":"2020"},{"key":"10.1016\/j.media.2026.104349_b47","series-title":"APTOS 2019 blindness detection","author":"Karthik","year":"2019"},{"issue":"2","key":"10.1016\/j.media.2026.104349_b48","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","article-title":"Seven-point checklist and skin lesion classification using multitask multimodal neural nets","volume":"23","author":"Kawahara","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"12","key":"10.1016\/j.media.2026.104349_b49","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.3390\/e23121608","article-title":"Empirical frequentist coverage of deep learning uncertainty quantification procedures","volume":"23","author":"Kompa","year":"2021","journal-title":"Entropy"},{"key":"10.1016\/j.media.2026.104349_b50","series-title":"International Workshop on Trustworthy Machine Learning for Healthcare","first-page":"163","article-title":"Conformal prediction masks: Visualizing uncertainty in medical imaging","author":"Kutiel","year":"2023"},{"key":"10.1016\/j.media.2026.104349_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102830","article-title":"Trustworthy clinical AI solutions: A unified review of uncertainty quantification in deep learning models for medical image analysis","volume":"150","author":"Lambert","year":"2024","journal-title":"Artif. Intell. Med."},{"issue":"6","key":"10.1016\/j.media.2026.104349_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2022.100512","article-title":"Deepdrid: Diabetic retinopathy\u2014grading and image quality estimation challenge","volume":"3","author":"Liu","year":"2022","journal-title":"Patterns"},{"key":"10.1016\/j.media.2026.104349_b53","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12008","article-title":"Fair conformal predictors for applications in medical imaging","volume":"vol. 36","author":"Lu","year":"2022"},{"issue":"2","key":"10.1016\/j.media.2026.104349_b54","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41592-023-02151-z","article-title":"Metrics reloaded: recommendations for image analysis validation","volume":"21","author":"Maier-Hein","year":"2024","journal-title":"Nature Methods"},{"key":"10.1016\/j.media.2026.104349_b55","series-title":"Th\u00e9orie analytique des probabilit\u00e9s","author":"marquis de Laplace","year":"1820"},{"key":"10.1016\/j.media.2026.104349_b56","unstructured":"Maurer, A., Pontil, M., 2009. Empirical bernstein bounds and sample variance penalization. In: Proc. Conference on Learning Theory - COLT."},{"key":"10.1016\/j.media.2026.104349_b57","series-title":"Adding error bars to evals: A statistical approach to language model evaluations","author":"Miller","year":"2024"},{"issue":"3","key":"10.1016\/j.media.2026.104349_b58","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1137\/1138055","article-title":"On multivariate skewness and kurtosis","volume":"38","author":"M\u00f3ri","year":"1994","journal-title":"Theory Probab. Appl."},{"issue":"2","key":"10.1016\/j.media.2026.104349_b59","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1111\/j.2041-210x.2012.00261.x","article-title":"A general and simple method for obtaining R2 from generalized linear mixed-effects models","volume":"4","author":"Nakagawa","year":"2013","journal-title":"Methods Ecol. Evol."},{"key":"10.1016\/j.media.2026.104349_b60","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"10.1016\/j.media.2026.104349_b61","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1177\/0962280207087173","article-title":"Comparison of non-parametric confidence intervals for the area under the ROC curve of a continuous-scale diagnostic test","volume":"17","author":"Qin","year":"2008","journal-title":"Stat. Methods Med. Res."},{"key":"10.1016\/j.media.2026.104349_b62","series-title":"Medical Imaging with Deep Learning","article-title":"Mura dataset: Towards radiologist-level abnormality detection in musculoskeletal radiographs","author":"Rajpurkar","year":"2017"},{"key":"10.1016\/j.media.2026.104349_b63","series-title":"Model evaluation, model selection, and algorithm selection in machine learning","author":"Raschka","year":"2018"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b64","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/s41597-021-00815-z","article-title":"A patient-centric dataset of images and metadata for identifying melanomas using clinical context","volume":"8","author":"Rotemberg","year":"2021","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104349_b65","doi-asserted-by":"crossref","DOI":"10.15626\/MP.2019.2058","article-title":"An introduction to the bootstrap: a versatile method to make inferences by using data-driven simulations","volume":"7","author":"Rousselet","year":"2023","journal-title":"Meta-Psychology"},{"key":"10.1016\/j.media.2026.104349_b66","series-title":"Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment","first-page":"90","article-title":"Semi-parametric estimation of the area under the precision-recall curve","volume":"9787","author":"Sahiner","year":"2016"},{"issue":"4","key":"10.1016\/j.media.2026.104349_b67","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1002\/bimj.201100134","article-title":"The empirical coverage of confidence intervals: Point estimates and confidence intervals for confidence levels","volume":"54","author":"Schall","year":"2012","journal-title":"Biom. J."},{"key":"10.1016\/j.media.2026.104349_b68","series-title":"Constructing confidence intervals for\u2019the\u2019generalization error\u2013a comprehensive benchmark study","author":"Schulz-K\u00fcmpel","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2026.104349_b69","doi-asserted-by":"crossref","first-page":"92","DOI":"10.25080\/Majora-92bf1922-011","article-title":"Statsmodels: econometric and statistical modeling with python.","volume":"7","author":"Seabold","year":"2010","journal-title":"SciPy"},{"key":"10.1016\/j.media.2026.104349_b70","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.neuroimage.2017.06.061","article-title":"Cross-validation failure: Small sample sizes lead to large error bars","volume":"180","author":"Varoquaux","year":"2018","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.104349_b71","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1007\/978-1-0716-3195-9_20","article-title":"Evaluating machine learning models and their diagnostic value","author":"Varoquaux","year":"2023","journal-title":"Mach. Learn. Brain Disord."},{"issue":"3","key":"10.1016\/j.media.2026.104349_b72","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nature Methods"},{"key":"10.1016\/j.media.2026.104349_b73","series-title":"All of Statistics: a Concise Course in Statistical Inference","author":"Wasserman","year":"2004"},{"key":"10.1016\/j.media.2026.104349_b74","series-title":"Introduction to Robust Estimation and Hypothesis Testing","author":"Wilcox","year":"2012"},{"issue":"158","key":"10.1016\/j.media.2026.104349_b75","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/01621459.1927.10502953","article-title":"Probable inference, the law of succession, and statistical inference","volume":"22","author":"Wilson","year":"1927","journal-title":"J. Amer. Statist. Assoc."},{"key":"10.1016\/j.media.2026.104349_b76","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2024.1505692","article-title":"Evolution of artificial intelligence in healthcare: a 30-year bibliometric study","volume":"11","author":"Xie","year":"2025","journal-title":"Front. Med."},{"key":"10.1016\/j.media.2026.104349_b77","series-title":"Covid-ct-dataset: a ct scan dataset about covid-19","author":"Yang","year":"2020"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526004184?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526004184?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T01:41:11Z","timestamp":1793670071000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526004184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":77,"alternative-id":["S1361841526004184"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104349","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Performance uncertainty in medical image analysis: A large-scale investigation of confidence intervals","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104349","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104349"}}