{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T03:49:05Z","timestamp":1793332145479,"version":"4.5.0"},"reference-count":99,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006093","name":"Patient-Centered Outcomes Research Institute","doi-asserted-by":"publisher","award":["MS-1610-37115"],"award-info":[{"award-number":["MS-1610-37115"]}],"id":[{"id":"10.13039\/100006093","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U24AG074855"],"award-info":[{"award-number":["U24AG074855"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020475","name":"National Science Foundation Directorate for STEM Education","doi-asserted-by":"publisher","award":["DGE-1746891"],"award-info":[{"award-number":["DGE-1746891"]}],"id":[{"id":"10.13039\/100020475","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020475","name":"National Science Foundation Directorate for STEM Education","doi-asserted-by":"publisher","award":["DGE-2139757"],"award-info":[{"award-number":["DGE-2139757"]}],"id":[{"id":"10.13039\/100020475","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"National Heart Lung and Blood Institute","doi-asserted-by":"publisher","award":["R01HL169944"],"award-info":[{"award-number":["R01HL169944"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01-LM014784"],"award-info":[{"award-number":["R01-LM014784"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["R01-EB036013"],"award-info":[{"award-number":["R01-EB036013"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013130","name":"Center for Neuroscience and Regenerative Medicine","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["U01-NS111678"],"award-info":[{"award-number":["U01-NS111678"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01-NS082347"],"award-info":[{"award-number":["R01-NS082347"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000090","name":"US Office of Congressionally Directed Medical Research Programs","doi-asserted-by":"publisher","award":["W81XWH2010912"],"award-info":[{"award-number":["W81XWH2010912"]}],"id":[{"id":"10.13039\/100000090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000090","name":"US Office of Congressionally Directed Medical Research Programs","doi-asserted-by":"publisher","award":["HT94252510716"],"award-info":[{"award-number":["HT94252510716"]}],"id":[{"id":"10.13039\/100000090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000090","name":"US Office of Congressionally Directed Medical Research Programs","doi-asserted-by":"publisher","award":["HT94252410785"],"award-info":[{"award-number":["HT94252410785"]}],"id":[{"id":"10.13039\/100000090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000890","name":"National Multiple Sclerosis Society","doi-asserted-by":"publisher","award":["RG-1507-05243"],"award-info":[{"award-number":["RG-1507-05243"]}],"id":[{"id":"10.13039\/100000890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000890","name":"National Multiple Sclerosis Society","doi-asserted-by":"publisher","award":["FG-2008-36966"],"award-info":[{"award-number":["FG-2008-36966"]}],"id":[{"id":"10.13039\/100000890","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"National Institute of Mental Health","doi-asserted-by":"publisher","award":["R01MH121620"],"award-info":[{"award-number":["R01MH121620"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Institutes of Health National Cancer Institute","doi-asserted-by":"publisher","award":["R01-CA275015"],"award-info":[{"award-number":["R01-CA275015"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Institutes of Health National Cancer Institute","doi-asserted-by":"publisher","award":["R01-CA253923"],"award-info":[{"award-number":["R01-CA253923"]}],"id":[{"id":"10.13039\/100000054","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":[[2026,3]]},"DOI":"10.1016\/j.media.2026.103954","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T17:28:00Z","timestamp":1768930080000},"page":"103954","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["UNISELF: A unified network with instance normalization and self-ensembled lesion fusion for multiple sclerosis lesion segmentation"],"prefix":"10.1016","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1992-4636","authenticated-orcid":false,"given":"Jinwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5923-9097","authenticated-orcid":false,"given":"Lianrui","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4554-5058","authenticated-orcid":false,"given":"Blake E.","family":"Dewey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8634-8128","authenticated-orcid":false,"given":"Samuel W.","family":"Remedios","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3187-9903","authenticated-orcid":false,"given":"Yihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8711-1356","authenticated-orcid":false,"given":"Savannah P.","family":"Hays","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0053-2034","authenticated-orcid":false,"given":"Dzung L.","family":"Pham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0623-5188","authenticated-orcid":false,"given":"Ellen M.","family":"Mowry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5284-4681","authenticated-orcid":false,"given":"Scott D.","family":"Newsome","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7776-6472","authenticated-orcid":false,"given":"Peter A.","family":"Calabresi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6387-0714","authenticated-orcid":false,"given":"Shiv","family":"Saidha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4939-5085","authenticated-orcid":false,"given":"Aaron","family":"Carass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6553-0876","authenticated-orcid":false,"given":"Jerry L.","family":"Prince","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.103954_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.068","article-title":"Multi-branch convolutional neural network for multiple sclerosis lesion segmentation","volume":"196","author":"Aslani","year":"2019","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0002","series-title":"2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)","first-page":"781","article-title":"Scanner invariant multiple sclerosis lesion segmentation from MRI","author":"Aslani","year":"2020"},{"key":"10.1016\/j.media.2026.103954_bib0003","article-title":"RimNet: a deep 3D multimodal MRI architecture for paramagnetic rim lesion assessment in multiple sclerosis","volume":"28","author":"Barquero","year":"2020","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102789","article-title":"Synthseg: segmentation of brain MRI scans of any contrast and resolution without retraining","volume":"86","author":"Billot","year":"2023","journal-title":"Med. Image Anal."},{"issue":"5","key":"10.1016\/j.media.2026.103954_bib0005","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1109\/TMI.2016.2528821","article-title":"Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation","volume":"35","author":"Brosch","year":"2016","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2026.103954_bib0006","doi-asserted-by":"crossref","first-page":"2356","DOI":"10.1007\/s00330-019-06593-y","article-title":"Automated volumetric assessment with artificial neural networks might enable a more accurate assessment of disease burden in patients with multiple sclerosis","volume":"30","author":"Brugnara","year":"2020","journal-title":"Eur. Radiol."},{"issue":"6","key":"10.1016\/j.media.2026.103954_bib0007","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","article-title":"A computational approach to edge detection","author":"Canny","year":"1986","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.ynirp.2024.100195","article-title":"Image harmonization improves consistency of intra-rater delineations of MS lesions in heterogeneous MRI","volume":"4","author":"Carass","year":"2024","journal-title":"NeuroImage Reports"},{"key":"10.1016\/j.media.2026.103954_bib0009","doi-asserted-by":"crossref","unstructured":"Carass, A., Roy, S., Gherman, A., Reinhold, J. C., Jesson, A., Arbel, T., Maier, O., Handels, H., Ghafoorian, M., Platel, B., Birenbaum, A., Greenspan, H., Pham, D. L., Crainiceanu, C. M., Calabresi, P. A., Prince, J. L., Gray Roncal, W. R., Shinohara, R. T., Oguz, I., 2020. Evaluating white matter lesion segmentations with refined s\u00f8rensen-dice analysis 10, 8242.","DOI":"10.1038\/s41598-020-64803-w"},{"key":"10.1016\/j.media.2026.103954_bib0010","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.dib.2017.04.004","article-title":"Longitudinal multiple sclerosis lesion segmentation data resource","volume":"12","author":"Carass","year":"2017","journal-title":"Data Brief"},{"key":"10.1016\/j.media.2026.103954_bib0011","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.neuroimage.2016.12.064","article-title":"Longitudinal multiple sclerosis lesion segmentation: resource and challenge","volume":"148","author":"Carass","year":"2017","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2020.117471","article-title":"A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis","volume":"225","author":"Cerri","year":"2021","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0013","doi-asserted-by":"crossref","first-page":"S66","DOI":"10.1016\/0022-510X(93)90212-H","article-title":"Brain magnetic resonance imaging correlates of cognitive impairment in multiple sclerosis","volume":"115","author":"Comi","year":"1993","journal-title":"J. Neurol. Sci."},{"key":"10.1016\/j.media.2026.103954_bib0014","series-title":"MICCAI 2021-24th International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"126","article-title":"Msseg-2 challenge proceedings: multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure","author":"Commowick","year":"2021"},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0015","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-018-31911-7","article-title":"Objective evaluation of multiple sclerosis lesion segmentation using a data management and processing infrastructure","volume":"8","author":"Commowick","year":"2018","journal-title":"Sci. Rep."},{"key":"10.1016\/j.media.2026.103954_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2021.118589","article-title":"Multiple sclerosis lesions segmentation from multiple experts: the MICCAI 2016 challenge dataset","volume":"244","author":"Commowick","year":"2021","journal-title":"Neuroimage"},{"issue":"4","key":"10.1016\/j.media.2026.103954_bib0017","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/TMI.2007.906087","article-title":"An optimized blockwise nonlocal means denoising filter for 3D magnetic resonance images","volume":"27","author":"Coup\u00e9","year":"2008","journal-title":"IEEE Trans. Med. Imag."},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0018","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s00401-016-1636-z","article-title":"Slow expansion of multiple sclerosis iron rim lesions: pathology and 7 T magnetic resonance imaging","volume":"133","author":"Dal-Bianco","year":"2017","journal-title":"Acta Neuropathol."},{"key":"10.1016\/j.media.2026.103954_bib0019","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.mri.2019.05.041","article-title":"DeepHarmony: a deep learning approach to contrast harmonization across scanner changes","volume":"64","author":"Dewey","year":"2019","journal-title":"Mag. Reson. Im."},{"key":"10.1016\/j.media.2026.103954_bib0020","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M., 2016. A learned representation for artistic style. arXiv preprint arXiv: 1610.07629."},{"issue":"4","key":"10.1016\/j.media.2026.103954_bib0021","doi-asserted-by":"crossref","first-page":"626","DOI":"10.3174\/ajnr.A5556","article-title":"An automated statistical technique for counting distinct multiple sclerosis lesions","volume":"39","author":"Dworkin","year":"2018","journal-title":"Am. J. Neuroradiol."},{"key":"10.1016\/j.media.2026.103954_bib0022","series-title":"2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)","first-page":"472","article-title":"A self-adaptive network for multiple sclerosis lesion segmentation from multi-contrast MRI with various imaging sequences","author":"Feng","year":"2019"},{"issue":"2","key":"10.1016\/j.media.2026.103954_bib0023","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1212\/WNL.45.2.255","article-title":"Correlations between changes in disability and t2-weighted brain MRI activity in multiple sclerosis: a follow-up study","volume":"45","author":"Filippi","year":"1995","journal-title":"Neurology"},{"issue":"7","key":"10.1016\/j.media.2026.103954_bib0024","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1093\/brain\/awz144","article-title":"Assessment of lesions on magnetic resonance imaging in multiple sclerosis: practical guidelines","volume":"142","author":"Filippi","year":"2019","journal-title":"Brain"},{"issue":"3","key":"10.1016\/j.media.2026.103954_bib0025","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/S1474-4422(15)00393-2","article-title":"Mri criteria for the diagnosis of multiple sclerosis: magnims consensus guidelines","volume":"15","author":"Filippi","year":"2016","journal-title":"The Lancet Neurol."},{"key":"10.1016\/j.media.2026.103954_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2023.119912","article-title":"Cross\u2013scanner harmonization methods for structural MRI may need further work: a comparison study","volume":"269","author":"Gebre","year":"2023","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0027","series-title":"2024 IEEE Conference on Artificial Intelligence (CAI)","first-page":"557","article-title":"Exploring viability of test-time training: application to 3d segmentation in multiple sclerosis","author":"G\u00e9rin","year":"2024"},{"key":"10.1016\/j.media.2026.103954_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102872","article-title":"Adaptive diffusion priors for accelerated MRI reconstruction","volume":"88","author":"G\u00fcng\u00f6r","year":"2023","journal-title":"Med. Image Anal."},{"issue":"3","key":"10.1016\/j.media.2026.103954_bib0029","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1093\/brain\/awv398","article-title":"The topograpy of demyelination and neurodegeneration in the multiple sclerosis brain","volume":"139","author":"Haider","year":"2016","journal-title":"Brain"},{"issue":"6","key":"10.1016\/j.media.2026.103954_bib0030","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1097\/00004728-199211000-00001","article-title":"Use of fluid attenuated inversion recovery (FLAIR) pulse sequences in MRI of the brain","volume":"16","author":"Hajnal","year":"1992","journal-title":"J. Comput. Assist. Tomogr."},{"issue":"4","key":"10.1016\/j.media.2026.103954_bib0031","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1097\/00004728-199207000-00002","article-title":"High signal regions in normal white matter shown by heavily t2-weighted CSF nulled IR sequences","volume":"16","author":"Hajnal","year":"1992","journal-title":"J. Comput. Assist. Tomogr."},{"key":"10.1016\/j.media.2026.103954_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2022.105402","article-title":"Delve into multiple sclerosis (MS) lesion exploration: a modified attention U-net for MS lesion segmentation in brain MRI","volume":"145","author":"Hashemi","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103954_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2020.117012","article-title":"Fastsurfer-a fast and accurate deep learning based neuroimaging pipeline","volume":"219","author":"Henschel","year":"2020","journal-title":"Neuroimage"},{"issue":"7","key":"10.1016\/j.media.2026.103954_bib0034","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1002\/sim.4780090710","article-title":"More powerful procedures for multiple significance testing","volume":"9","author":"Hochberg","year":"1990","journal-title":"Stat. Med."},{"key":"10.1016\/j.media.2026.103954_bib0035","series-title":"International Conference on Machine Learning","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"issue":"2","key":"10.1016\/j.media.2026.103954_bib0036","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"Nnu-Net.: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0037","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"10.1016\/j.media.2026.103954_bib0038","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"11","article-title":"The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation","author":"J\u00e9gou","year":"2017"},{"key":"10.1016\/j.media.2026.103954_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106726","article-title":"A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation","volume":"157","author":"Jiang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103954_bib0040","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain, September 16\u201320, 2018, Proceedings, Part I","first-page":"682","article-title":"On the effect of inter-observer variability for a reliable estimation of uncertainty of medical image segmentation","author":"Jungo","year":"2018"},{"key":"10.1016\/j.media.2026.103954_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.102312","article-title":"DeepLesionBrain: towards a broader deep-learning generalization for multiple sclerosis lesion segmentation","volume":"76","author":"Kamraoui","year":"2022","journal-title":"Med. Image Anal."},{"issue":"5","key":"10.1016\/j.media.2026.103954_bib0042","first-page":"661","article-title":"Correlation between magnetic resonance imaging findings and lesion development in chronic, active multiple sclerosis","volume":"34","author":"Katz","year":"1993","journal-title":"Annals of Neurol. Off. J. Am. Neurolog. Assoc. Child Neurol. Soc."},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0043","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1093\/brain\/awy296","article-title":"Quantitative susceptibility mapping identifies inflammation in a subset of chronic multiple sclerosis lesions","volume":"142","author":"Kaunzner","year":"2019","journal-title":"Brain"},{"key":"10.1016\/j.media.2026.103954_bib0044","unstructured":"Kingma, D. P., Ba, J., 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv: 1412.6980."},{"key":"10.1016\/j.media.2026.103954_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.nicl.2022.103194","article-title":"From pathology to MRI and back: clinically relevant biomarkers of multiple sclerosis lesions","author":"Kolb","year":"2022","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0046","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","article-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy","volume":"51","author":"Kuncheva","year":"2003","journal-title":"Mach. Learn."},{"key":"10.1016\/j.media.2026.103954_bib0047","article-title":"Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE","volume":"27","author":"La Rosa","year":"2020","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0048","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.103954_bib0049","series-title":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","first-page":"1","article-title":"Quantifying white matter hyperintensity and brain volumes in heterogeneous clinical and low-field portable MRI","author":"Laso","year":"2024"},{"key":"10.1016\/j.media.2026.103954_bib0050","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s12021-017-9348-7","article-title":"A novel public MR image dataset of multiple sclerosis patients with lesion segmentations based on multi-rater consensus","volume":"16","author":"Lesjak","year":"2018","journal-title":"Neuroinformatics"},{"key":"10.1016\/j.media.2026.103954_bib0051","article-title":"MS Lesion segmentation: revisiting weighting mechanisms for federated learning","volume":"17","author":"Liu","year":"2023","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.media.2026.103954_bib0052","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"444","article-title":"Moddrop++: a dynamic filter network with intra-subject co-training for multiple sclerosis lesion segmentation with missing modalities","author":"Liu","year":"2022"},{"key":"10.1016\/j.media.2026.103954_bib0053","article-title":"Fully automated detection of paramagnetic rims in multiple sclerosis lesions on 3T susceptibility-based MR imaging","volume":"32","author":"Lou","year":"2021","journal-title":"NeuroImage: Clinical"},{"issue":"6","key":"10.1016\/j.media.2026.103954_bib0054","doi-asserted-by":"crossref","first-page":"2680","DOI":"10.1109\/JBHI.2022.3151741","article-title":"Multiple sclerosis lesion analysis in brain magnetic resonance images: techniques and clinical applications","volume":"26","author":"Ma","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.media.2026.103954_bib0055","unstructured":"Malinin, A., Athanasopoulos, A., Barakovic, M., Cuadra, M. B., Gales, M. J. F., Granziera, C., Graziani, M., Kartashev, N., Kyriakopoulos, K., Lu, P.-J., et al., 2022. Shifts 2.0: Extending the dataset of real distributional shifts. arXiv preprint arXiv: 2206.15407."},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0056","doi-asserted-by":"crossref","first-page":"5068","DOI":"10.1038\/s41598-020-61808-3","article-title":"Test-time augmentation for deep learning-based cell segmentation on microscopy images","volume":"10","author":"Moshkov","year":"2020","journal-title":"Sci. Rep."},{"issue":"9","key":"10.1016\/j.media.2026.103954_bib0057","doi-asserted-by":"crossref","first-page":"2306","DOI":"10.1109\/TMI.2021.3075856","article-title":"Results of the 2020 fastMRI challenge for machine learning MR image reconstruction","volume":"40","author":"Muckley","year":"2021","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2026.103954_bib0058","unstructured":"Nado, Z., Padhy, S., Sculley, D., D\u2019Amour, A., Lakshminarayanan, B., Snoek, J., 2020. Evaluating prediction-time batch normalization for robustness under covariate shift. arXiv preprint arXiv: 2006.10963."},{"key":"10.1016\/j.media.2026.103954_bib0059","article-title":"Scanner-specific optimisation of automated lesion segmentation in MS","volume":"44","author":"van Nederpelt","year":"2024","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0060","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: an empirical study","volume":"11","author":"Opitz","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.media.2026.103954_bib0061","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2021.106236","article-title":"TorchIO: a python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning","volume":"208","author":"P\u00e9rez-Garc\u00eda","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.media.2026.103954_bib0062","series-title":"Dataset Shift in Machine Learning","author":"Qui\u00f1onero-Candela","year":"2022"},{"key":"10.1016\/j.media.2026.103954_bib0063","series-title":"Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) Held in Conjunction with the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)","first-page":"118","article-title":"Self-supervised super-resolution for anisotropic MR images with and without slice gap","volume":"Vol. 14288","author":"Remedios","year":"2023"},{"key":"10.1016\/j.media.2026.103954_bib0064","series-title":"International Encyclopedia of Statistical Science","first-page":"1658","article-title":"Wilcoxon-signed-rank test","author":"Rey","year":"2011"},{"key":"10.1016\/j.media.2026.103954_bib0065","series-title":"Medical Imaging 2025: Image Processing","first-page":"592","article-title":"Unique MS lesion identification from MRI","volume":"Vol. 13406","author":"Rivas","year":"2025"},{"key":"10.1016\/j.media.2026.103954_bib0066","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107021","article-title":"Boosting multiple sclerosis lesion segmentation through attention mechanism","volume":"161","author":"Rondinella","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.103954_bib0067","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.103954_bib0068","series-title":"7th International Symposium on Biomedical Imaging (ISBI 2010)","first-page":"932","article-title":"MR Contrast synthesis for lesion segmentation","author":"Roy","year":"2010"},{"issue":"4","key":"10.1016\/j.media.2026.103954_bib0069","doi-asserted-by":"crossref","first-page":"3774","DOI":"10.1016\/j.neuroimage.2011.11.032","article-title":"An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis","volume":"59","author":"Schmidt","year":"2012","journal-title":"Neuroimage"},{"issue":"2","key":"10.1016\/j.media.2026.103954_bib0070","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1016\/j.neuroimage.2009.09.005","article-title":"A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions","volume":"49","author":"Shiee","year":"2010","journal-title":"Neuroimage"},{"issue":"1","key":"10.1016\/j.media.2026.103954_bib0071","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"10.1016\/j.media.2026.103954_bib0072","series-title":"3D Segmentation in the clinic: a grand challenge II: MS lesion segmentation","first-page":"1","author":"Styner","year":"2008"},{"key":"10.1016\/j.media.2026.103954_bib0073","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20730","article-title":"Self-supervised pre-training of swin transformers for 3D medical image analysis","author":"Tang","year":"2022"},{"key":"10.1016\/j.media.2026.103954_bib0074","series-title":"Medical Imaging 2022: Biomedical Applications in Molecular, Structural, and Functional Imaging","first-page":"578","article-title":"Multiple sclerosis brain lesion segmentation with different architecture ensembles","volume":"Vol. 12036","author":"Tohidi","year":"2022"},{"key":"10.1016\/j.media.2026.103954_bib0075","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.neuroimage.2017.04.034","article-title":"Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach","volume":"155","author":"Valverde","year":"2017","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0076","article-title":"One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks","volume":"21","author":"Valverde","year":"2019","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0077","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2019.01.103","article-title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","volume":"338","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"issue":"10","key":"10.1016\/j.media.2026.103954_bib0078","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1038\/nrneurol.2015.157","article-title":"Evidence-based guidelines: MAGNIMS consensus guidelines on the use of MRI in multiple sclerosis\u2013establishing disease prognosis and monitoring patients","volume":"11","author":"Wattjes","year":"2015","journal-title":"Nat. Rev. Neurol."},{"key":"10.1016\/j.media.2026.103954_bib0079","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22\u201326, 2013, Proceedings, Part I 16","first-page":"735","article-title":"Multiple sclerosis lesion segmentation using dictionary learning and sparse coding","author":"Weiss","year":"2013"},{"key":"10.1016\/j.media.2026.103954_bib0080","article-title":"LST-AI: a deep learning ensemble for accurate ms lesion segmentation","volume":"42","author":"Wiltgen","year":"2024","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0081","doi-asserted-by":"crossref","unstructured":"Wynen, M., Gordaliza, P. M., Istasse, M., St\u00f6lting, A., Maggi, P., Macq, B., Cuadra, M. B., 2025. ConfLUNet: Multiple sclerosis lesion instance segmentation in presence of confluent lesions. arXiv preprint arXiv: 2505.22537.","DOI":"10.1016\/j.compbiomed.2025.110919"},{"issue":"12","key":"10.1016\/j.media.2026.103954_bib0082","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.1109\/TMI.2021.3084288","article-title":"Time-dependent deep image prior for dynamic MRI","volume":"40","author":"Yoo","year":"2021","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2026.103954_bib0083","series-title":"Medical Imaging 2023: Image Processing","first-page":"195","article-title":"Domain generalization for robust MS lesion segmentation","volume":"Vol. 12464","author":"Zhang","year":"2023"},{"key":"10.1016\/j.media.2026.103954_bib0084","article-title":"QSMRim-Net: Imbalance-aware learning for identification of chronic active multiple sclerosis lesions on quantitative susceptibility maps","volume":"34","author":"Zhang","year":"2022","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0085","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part III 22","first-page":"338","article-title":"Multiple sclerosis lesion segmentation with tiramisu and 2.5D stacked slices","author":"Zhang","year":"2019"},{"key":"10.1016\/j.media.2026.103954_bib0086","article-title":"ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation","volume":"32","author":"Zhang","year":"2021","journal-title":"NeuroImage: Clinical"},{"key":"10.1016\/j.media.2026.103954_bib0087","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10868","article-title":"Efficient folded attention for medical image reconstruction and segmentation","volume":"Vol. 35","author":"Zhang","year":"2021"},{"key":"10.1016\/j.media.2026.103954_bib0088","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part III 22","first-page":"411","article-title":"RSANet: Recurrent slice-wise attention network for multiple sclerosis lesion segmentation","author":"Zhang","year":"2019"},{"key":"10.1016\/j.media.2026.103954_bib0089","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2020.116579","article-title":"Fidelity imposed network edit (FINE) for solving ill-posed image reconstruction","volume":"211","author":"Zhang","year":"2020","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.neuroimage.2023.119886","article-title":"LARO: Learned acquisition and reconstruction optimization to accelerate quantitative susceptibility mapping","volume":"268","author":"Zhang","year":"2023","journal-title":"Neuroimage"},{"key":"10.1016\/j.media.2026.103954_bib0091","unstructured":"Zhang, J., Zhang, H., Sabuncu, M., Spincemaille, P., Nguyen, T., Wang, Y., 2020b. Probabilistic dipole inversion for adaptive quantitative susceptibility mapping. arXiv preprint arXiv: 2009.04251."},{"key":"10.1016\/j.media.2026.103954_bib0092","series-title":"Proceedings of SPIE Medical Imaging (SPIE-MI 2024), San Diego, CA, February 18\u201322, 2024","first-page":"635","article-title":"Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation","volume":"Vol. 12930","author":"Zhang","year":"2024"},{"key":"10.1016\/j.media.2026.103954_bib0093","series-title":"21th International Symposium on Biomedical Imaging (ISBI 2024)","first-page":"1","article-title":"Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion","author":"Zhang","year":"2024"},{"key":"10.1016\/j.media.2026.103954_bib0094","series-title":"Proceedings of SPIE Medical Imaging (SPIE-MI 2025), San Diego, CA, February 16\u201320, 2025","article-title":"Bi-directional MS lesion filling and synthesis using denoising diffusion implicit model-based lesion repainting","author":"Zhang","year":"2025"},{"issue":"3","key":"10.1016\/j.media.2026.103954_bib0095","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1109\/TMI.2020.3037187","article-title":"SMORE: a self-supervised anti-aliasing and super-resolution algorithm for MRI using deep learning","volume":"40","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2026.103954_bib0096","series-title":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","first-page":"1047","article-title":"Robust white matter hyperintensity segmentation on unseen domain","author":"Zhao","year":"2021"},{"issue":"4","key":"10.1016\/j.media.2026.103954_bib0097","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/42.363096","article-title":"Morphometric analysis of white matter lesions in MR images: method and validation","volume":"13","author":"Zijdenbos","year":"1994","journal-title":"IEEE Trans. Med. Imag."},{"key":"10.1016\/j.media.2026.103954_bib0098","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2023.102285","article-title":"HACA3: a unified approach for multi-site MR image harmonization","volume":"109","author":"Zuo","year":"2023","journal-title":"Comput. Med. Imag. Graph."},{"key":"10.1016\/j.media.2026.103954_bib0099","series-title":"MICCAI Workshop on Data Augmentation, Labelling, and Imperfections","first-page":"54","article-title":"Disentangling a single MR modality","author":"Zuo","year":"2022"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600023X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S136184152600023X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:27:36Z","timestamp":1770683256000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S136184152600023X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":99,"alternative-id":["S136184152600023X"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.103954","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UNISELF: A unified network with instance normalization and self-ensembled lesion fusion for multiple sclerosis lesion segmentation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.103954","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":"103954"}}