{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:07:00Z","timestamp":1779419220804,"version":"3.53.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032065926","type":"print"},{"value":"9783032065933","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06593-3_14","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T12:37:40Z","timestamp":1759063060000},"page":"147-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Rater Calibration Error Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6221-5443","authenticated-orcid":false,"given":"Meritxell","family":"Riera-Mar\u00edn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9241-8479","authenticated-orcid":false,"given":"Javier Garc\u00eda","family":"L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4788-6668","authenticated-orcid":false,"given":"J\u00falia","family":"Rodr\u00edguez-Comas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9227-6826","authenticated-orcid":false,"given":"Miguel A. Gonz\u00e1lez","family":"Ballester","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5992-1520","authenticated-orcid":false,"given":"Adrian","family":"Galdran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Armato, S.G., III., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915\u2013931 (2011). https:\/\/doi.org\/10.1118\/1.3528204","DOI":"10.1118\/1.3528204"},{"issue":"351","key":"14_CR2","first-page":"1","volume":"23","author":"I Arrieta-Ibarra","year":"2022","unstructured":"Arrieta-Ibarra, I., Gujral, P., Tannen, J., Tygert, M., Xu, C.: Metrics of calibration for probabilistic predictions. J. Mach. Learn. Res. 23(351), 1\u201354 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR3","doi-asserted-by":"publisher","unstructured":"Bucarelli, M.S., Cassano, L., Siciliano, F., Mantrach, A., Silvestri, F.: Leveraging inter-rater agreement for classification in the presence of noisy labels. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3439\u20133448 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00335, iSSN: 2575-7075","DOI":"10.1109\/CVPR52729.2023.00335"},{"issue":"6","key":"14_CR4","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1038\/s41551-022-00988-x","volume":"7","author":"M Chua","year":"2023","unstructured":"Chua, M., Kim, D., Choi, J., Lee, N.G., Deshpande, V., Schwab, J., Lev, M.H., Gonzalez, R.G., Gee, M.S., Do, S.: Tackling prediction uncertainty in machine learning for healthcare. Nature Biomed. Eng. 7(6), 711\u2013718 (2023). https:\/\/doi.org\/10.1038\/s41551-022-00988-x","journal-title":"Nature Biomed. Eng."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Gruber, S.G., Buettner, F.: Better uncertainty calibration via proper scores for classification and beyond. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-0627"},{"issue":"1","key":"14_CR6","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/S0169-7439(01)00211-8","volume":"62","author":"J Huang","year":"2002","unstructured":"Huang, J., Brennan, D., Sattler, L., Alderman, J., Lane, B., O\u2019Mathuna, C.: A comparison of calibration methods based on calibration data size and robustness. Chemom. Intell. Lab. Syst. 62(1), 25\u201335 (2002). https:\/\/doi.org\/10.1016\/S0169-7439(01)00211-8","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"14_CR7","unstructured":"Iakubovskii, P.: Segmentation Models Pytorch (2019). https:\/\/github.com\/qubvel\/segmentation_models.pytorch, publication Title: GitHub repository"},{"key":"14_CR8","doi-asserted-by":"publisher","unstructured":"Ji, W., et al.: Learning calibrated medical image segmentation via multi-rater agreement modeling. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12336\u201312346 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01216","DOI":"10.1109\/CVPR46437.2021.01216"},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Jungo, A., Balsiger, F., Reyes, M.: Analyzing the quality and challenges of uncertainty estimations for brain tumor segmentation. Front. Neurosci. 14 (2020). https:\/\/doi.org\/10.3389\/fnins.2020.00282","DOI":"10.3389\/fnins.2020.00282"},{"key":"14_CR10","unstructured":"Kull, M., Perello\u00a0Nieto, M., K\u00e4ngsepp, M., Silva\u00a0Filho, T., Song, H., Flach, P.: Beyond temperature scaling: obtaining well-calibrated multi-class probabilities with Dirichlet calibration. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"14_CR11","doi-asserted-by":"publisher","unstructured":"Kumar, J.R.H., et al.: Ch\u00e1k\u1e63u: a glaucoma specific fundus image database. Sci. Data 10(1), 70 (2023). https:\/\/doi.org\/10.1038\/s41597-023-01943-4","DOI":"10.1038\/s41597-023-01943-4"},{"key":"14_CR12","doi-asserted-by":"publisher","unstructured":"Li, H.B., et\u00a0al.: QUBIQ: uncertainty quantification for biomedical image segmentation challenge (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.18435","DOI":"10.48550\/arXiv.2405.18435"},{"key":"14_CR13","unstructured":"Nixon, J., Dusenberry, M.W., Zhang, L., Jerfel, G., Tran, D.: Measuring calibration in deep learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2019)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Popordanoska, T., Sayer, R., Blaschko, M.B.: A consistent and differentiable LP canonical calibration error estimator. In: Proceedings of the 36th International Conference on Neural Information Processing Systems, pp. 7933\u20137946 (2022)","DOI":"10.52202\/068431-0576"},{"key":"14_CR15","unstructured":"Roelofs, R., Cain, N., Shlens, J., Mozer, M.C.: Mitigating bias in calibration error estimation. In: Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, pp. 4036\u20134054. PMLR (2022)"},{"issue":"9","key":"14_CR16","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1007\/s10994-023-06336-7","volume":"112","author":"T Silva Filho","year":"2023","unstructured":"Silva Filho, T., Song, H., Perello-Nieto, M., Santos-Rodriguez, R., Kull, M., Flach, P.: Classifier calibration: a survey on how to assess and improve predicted class probabilities. Mach. Learn. 112(9), 3211\u20133260 (2023). https:\/\/doi.org\/10.1007\/s10994-023-06336-7","journal-title":"Mach. Learn."},{"key":"14_CR17","unstructured":"Sorkhei, M., et al.: CSAW-M: an ordinal classification dataset for benchmarking mammographic masking of cancer. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol.\u00a01 (2021)"},{"issue":"5","key":"14_CR18","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s10444-023-10068-6","volume":"49","author":"M Tygert","year":"2023","unstructured":"Tygert, M.: Calibration of p-values for calibration and for deviation of a subpopulation from the full population. Adv. Comput. Math. 49(5), 70 (2023). https:\/\/doi.org\/10.1007\/s10444-023-10068-6","journal-title":"Adv. Comput. Math."},{"key":"14_CR19","unstructured":"Vaicenavicius, J., Widmann, D., Andersson, C., Lindsten, F., Roll, J., Sch\u00f6n, T.: Evaluating model calibration in classification. In: Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol.\u00a089, pp. 3459\u20133467. PMLR (2019)"},{"issue":"7","key":"14_CR20","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1109\/TMI.2004.828354","volume":"23","author":"S Warfield","year":"2004","unstructured":"Warfield, S., Zou, K., Wells, W.: Simultaneous truth and performance level estimation (staple): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903\u2013921 (2004). https:\/\/doi.org\/10.1109\/TMI.2004.828354","journal-title":"IEEE Trans. Med. Imaging"},{"key":"14_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-030-77211-6_2","volume-title":"Artificial Intelligence in Medicine","author":"J Wei","year":"2021","unstructured":"Wei, J., Suriawinata, A., Ren, B., Liu, X., Lisovsky, M., Vaickus, L., Brown, C., Baker, M., Tomita, N., Torresani, L., Wei, J., Hassanpour, S.: A petri dish for histopathology image analysis. In: Tucker, A., Henriques Abreu, P., Cardoso, J., Pereira Rodrigues, P., Ria\u00f1o, D. (eds.) AIME 2021. LNCS (LNAI), vol. 12721, pp. 11\u201324. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77211-6_2"},{"key":"14_CR22","unstructured":"Widmann, D., Lindsten, F., Zachariah, D.: Calibration tests in multi-class classification: a unifying framework. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"14_CR23","unstructured":"Wundram, A.M., et al.: Leveraging Probabilistic Segmentation Models for Improved Glaucoma Diagnosis: A Clinical Pipeline Approach. In: Medical Imaging with Deep Learning (2024)"},{"key":"14_CR24","unstructured":"Zhang, J., Kailkhura, B., Han, T.Y.J.: Mix-n-match: ensemble and compositional methods for uncertainty calibration in deep learning. In: Proceedings of the 37th International Conference on Machine Learning, pp. 11117\u201311128. PMLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Uncertainty for Safe Utilization of Machine Learning in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06593-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:49:26Z","timestamp":1779418166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06593-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032065926","9783032065933"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06593-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"UNSURE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"unsure2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/unsuremiccai.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}