{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T03:11:50Z","timestamp":1778296310560,"version":"3.51.4"},"posted":{"date-parts":[[2026,3,10]]},"group-title":"Radiology and Imaging","reference-count":61,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,5,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Current multiple sclerosis (MS) diagnosis relies primarily on focal white matter lesions (WMLs), which are frequently mimicked by other conditions. Normal-appearing white matter (NAWM) harbours complementary pathological information but remains clinically underutilised because NAWM alterations are macroscopically occult on routine scans and require non-routine quantitative imaging to visualise. Here, we show that NAWM-related diagnostic information can be recovered from routine structural MRI using a cross-modal deep-learning model. We developed DeepMS, a model co-trained on diffusion and structural MRI that operates solely on structural MRI at deployment. DeepMS achieved ROC-AUCs of 0.968 internally (n=837) and 0.940\u20130.974 across two international external cohorts (n=293 and n=1,756). In a multi-reader study, DeepMS outperformed the 2024 McDonald criteria imaging biomarkers. DeepMS retained robust performance after digital lesion removal and exhibited NAWM-dominant activation maps. Combined with established imaging biomarkers, DeepMS improved sensitivity (92.1% vs 74.8%) while maintaining high specificity (95.6% vs 92.3%) compared with corresponding biomarker composite based on the 2024 McDonald criteria. By decoding latent NAWM signals from routine scans and integrating them with WML features, this framework can potentially advance MS diagnosis beyond the current lesion-centric paradigm.<\/jats:p>","DOI":"10.64898\/2026.03.04.26347460","type":"posted-content","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T02:15:20Z","timestamp":1773195320000},"source":"Crossref","is-referenced-by-count":0,"title":["Diagnosis of Multiple Sclerosis Using Multimodal Deep Learning Integrating Lesion and Normal-Appearing White Matter: A Retrospective Study with International Multicentre External Validation"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4614-0804","authenticated-orcid":false,"given":"Jiajian","family":"Ma","sequence":"first","affiliation":[{"name":"Center for Data Science, New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0007-8054","authenticated-orcid":false,"given":"Valentin","family":"Stepanov","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0214-0605","authenticated-orcid":false,"given":"Wushuang","family":"Rui","sequence":"additional","affiliation":[{"name":"Department of Biology, New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsuan-Chih","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Data Science, New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5622-659X","authenticated-orcid":false,"given":"Maciej","family":"Lis","sequence":"additional","affiliation":[{"name":"Clinical Imaging Diagnostics Center, 5th Military Hospital with Polyclinic in Krakow, 30-901 Krakow, Poland"},{"name":"Department of Anatomy, Jagiellonian University Medical College, 31-008 Krakow, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksandra","family":"Stanek","sequence":"additional","affiliation":[{"name":"Clinical Imaging Diagnostics Center, 5th Military Hospital with Polyclinic in Krakow, 30-901 Krakow, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7095-7619","authenticated-orcid":false,"given":"Tomasz","family":"Puto","sequence":"additional","affiliation":[{"name":"Clinical Imaging Diagnostics Center, 5th Military Hospital with Polyclinic in Krakow, 30-901 Krakow, Poland"},{"name":"Department of Diagnostic Imaging, Faculty of Medicine, Andrzej Frycz Modrzewski Krakow University, 30-705 Krakow, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Lan","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jenny","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3115-1537","authenticated-orcid":false,"given":"Timothy","family":"Liu","sequence":"additional","affiliation":[{"name":"New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roshni","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6942-5164","authenticated-orcid":false,"given":"Matthew","family":"Breen","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8816-1076","authenticated-orcid":false,"given":"Matthew","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katharina","family":"Eikermann-Haerter","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0232-1636","authenticated-orcid":false,"given":"Timothy M.","family":"Shepherd","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4213-3050","authenticated-orcid":false,"given":"Dmitry S.","family":"Novikov","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-8683","authenticated-orcid":false,"given":"Kimberly A.","family":"O\u2019Neill","sequence":"additional","affiliation":[{"name":"Department of Neurology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1384-8591","authenticated-orcid":false,"given":"Els","family":"Fieremans","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7726-2514","authenticated-orcid":false,"given":"Yiqiu","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA"},{"name":"Center for Data Science, New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026050819500984000_2026.03.04.26347460v2.1","doi-asserted-by":"publisher","DOI":"10.1177\/135245852097084"},{"key":"2026050819500984000_2026.03.04.26347460v2.2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.20588"},{"key":"2026050819500984000_2026.03.04.26347460v2.3","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1016\/S1474-4422(25)00270-4","article-title":"Diagnosis of multiple sclerosis: 2024 revisions of the McDonald criteria","volume":"24","year":"2025","journal-title":"Lancet Neurol"},{"key":"2026050819500984000_2026.03.04.26347460v2.4","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1212\/WNL.0000000000003152","article-title":"The contemporary spectrum of multiple sclerosis misdiagnosis: A multicenter study","volume":"87","year":"2016","journal-title":"Neurology"},{"key":"2026050819500984000_2026.03.04.26347460v2.5","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1001\/jamaneurol.2023.4737","article-title":"Diagnostic performance of cortical lesions and the central vein sign in multiple sclerosis","volume":"81","year":"2024","journal-title":"JAMA Neurol"},{"key":"2026050819500984000_2026.03.04.26347460v2.6","doi-asserted-by":"crossref","unstructured":"Hemond, C. C. et al. Paramagnetic rim lesions are highly specific for multiple sclerosis in real-world data. Brain Commun. 7, fcaf211 (2025).","DOI":"10.1093\/braincomms\/fcaf211"},{"key":"2026050819500984000_2026.03.04.26347460v2.7","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.msard.2019.01.048","article-title":"Incidence of multiple sclerosis misdiagnosis in referrals to two academic centers","volume":"30","year":"2019","journal-title":"Mult. Scler. Relat. Disord"},{"key":"2026050819500984000_2026.03.04.26347460v2.8","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1177\/1352458520988148","article-title":"The frequency and characteristics of MS misdiagnosis in patients referred to the multiple sclerosis centre of Catalonia","volume":"27","year":"2021","journal-title":"Mult. Scler"},{"key":"2026050819500984000_2026.03.04.26347460v2.9","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1177\/13524585211067521","article-title":"The frequency and characteristics of multiple sclerosis misdiagnosis in Latin America: A referral center study in Buenos Aires, Argentina","volume":"28","year":"2022","journal-title":"Mult. Scler"},{"key":"2026050819500984000_2026.03.04.26347460v2.10","doi-asserted-by":"publisher","DOI":"10.1002\/ana.22521"},{"key":"2026050819500984000_2026.03.04.26347460v2.11","doi-asserted-by":"crossref","unstructured":"Elliott, C. et al. Abnormalities in normal-appearing white matter from which multiple sclerosis lesions arise. Brain Commun. 3, fcab176 (2021).","DOI":"10.1093\/braincomms\/fcab176"},{"key":"2026050819500984000_2026.03.04.26347460v2.12","doi-asserted-by":"publisher","DOI":"10.1101\/2025.11.07.25339773"},{"key":"2026050819500984000_2026.03.04.26347460v2.13","doi-asserted-by":"crossref","first-page":"e01194","DOI":"10.1002\/brb3.1194","article-title":"Diffusion tensor imaging and disability progression in multiple sclerosis: A 4-year follow-up study","volume":"9","year":"2019","journal-title":"Brain Behav"},{"key":"2026050819500984000_2026.03.04.26347460v2.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jare.2025.08.059"},{"key":"2026050819500984000_2026.03.04.26347460v2.15","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-10550-1"},{"key":"2026050819500984000_2026.03.04.26347460v2.16","doi-asserted-by":"crossref","first-page":"1384073","DOI":"10.3389\/fnins.2024.1384073","article-title":"Differentiation of hemispheric white matter lesions in migraine and multiple sclerosis with similar radiological features using advanced MRI","volume":"18","year":"2024","journal-title":"Front. Neurosci"},{"key":"2026050819500984000_2026.03.04.26347460v2.17","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(25)00304-7"},{"key":"2026050819500984000_2026.03.04.26347460v2.18","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.mri.2023.09.010","article-title":"A systematic review of microstructural abnormalities in multiple sclerosis detected with NODDI and DTI models of diffusion-weighted magnetic resonance imaging","volume":"104","year":"2023","journal-title":"Magn. Reson. Imaging"},{"key":"2026050819500984000_2026.03.04.26347460v2.19","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.1518"},{"key":"2026050819500984000_2026.03.04.26347460v2.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.06.006"},{"key":"2026050819500984000_2026.03.04.26347460v2.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119290"},{"key":"2026050819500984000_2026.03.04.26347460v2.22","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A. , et al. Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images. arXiv [eess.IV] (2022).","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"2026050819500984000_2026.03.04.26347460v2.23","unstructured":"Wu, L. , Zhuang, J. & Chen, H. Large-scale 3D medical image pre-training with geometric context priors. arXiv [cs.CV] (2024)."},{"key":"2026050819500984000_2026.03.04.26347460v2.24","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.21049"},{"key":"2026050819500984000_2026.03.04.26347460v2.25","doi-asserted-by":"crossref","first-page":"e220058","DOI":"10.1148\/ryai.220058","article-title":"The university of California San Francisco preoperative diffuse glioma MRI dataset","volume":"4","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"2026050819500984000_2026.03.04.26347460v2.26","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1038\/s41597-024-03021-9","article-title":"A large open access dataset of brain metastasis 3D segmentations on MRI with clinical and imaging information","volume":"11","year":"2024","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.12.064"},{"key":"2026050819500984000_2026.03.04.26347460v2.28","doi-asserted-by":"crossref","first-page":"180308","DOI":"10.1038\/sdata.2018.308","article-title":"A mind-brain-body dataset of MRI, EEG, cognition, emotion, and peripheral physiology in young and old adults","volume":"6","year":"2019","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.29","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1038\/s41597-022-01875-5","article-title":"ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset","volume":"9","year":"2022","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.30","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/s41597-023-02386-7","article-title":"An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II","volume":"10","year":"2023","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.31","unstructured":"Commowick, O. , Cervenansky, F. & Ameli, R. MSSEG challenge proceedings: Multiple sclerosis lesions segmentation challenge using a data management and processing infrastructure. Medical Image Computing and Computer-Assisted Intervention (2016)."},{"key":"2026050819500984000_2026.03.04.26347460v2.32","unstructured":"Commowick, O. , Cervenansky, F. , Cotton, F. & Dojat, M . MSSEG-2 Challenge Proceedings: Multiple Sclerosis New Lesions Segmentation Challenge Using a Data Management and Processing Infrastructure. in Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021) 126 (Strasbourg, France, 2021)."},{"key":"2026050819500984000_2026.03.04.26347460v2.33","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/s41597-024-03418-6","article-title":"Multiparametric MRI dataset for susceptibility-based radiomic feature extraction and analysis","volume":"11","year":"2024","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.34","unstructured":"MRBrainS18: MR Brain Segmentation Challenge. https:\/\/MRBrainS18.isi.uu.nl\/ (2018)."},{"key":"2026050819500984000_2026.03.04.26347460v2.35","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2019.2905770"},{"key":"2026050819500984000_2026.03.04.26347460v2.36","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-016-9301-1"},{"key":"2026050819500984000_2026.03.04.26347460v2.37","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-017-9348-7"},{"key":"2026050819500984000_2026.03.04.26347460v2.38","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.1038\/s41597-025-05346-5","article-title":"PediMS: A pediatric multiple sclerosis lesion segmentation dataset","volume":"12","year":"2025","journal-title":"Sci. Data"},{"key":"2026050819500984000_2026.03.04.26347460v2.39","doi-asserted-by":"crossref","unstructured":"Popa, M. & Visa, G. A. PediDemi -- A Pediatric Demyelinating Lesion Segmentation Dataset. arXiv [eess.IV] (2025).","DOI":"10.59275\/j.melba.2025-123f"},{"key":"2026050819500984000_2026.03.04.26347460v2.40","doi-asserted-by":"crossref","first-page":"108530","DOI":"10.1016\/j.compbiomed.2024.108530","article-title":"Improving the classification of multiple sclerosis and cerebral small vessel disease with interpretable transfer attention neural network","volume":"176","year":"2024","journal-title":"Comput. Biol. Med"},{"key":"2026050819500984000_2026.03.04.26347460v2.41","doi-asserted-by":"crossref","first-page":"1351387","DOI":"10.3389\/fnins.2024.1351387","article-title":"A joint model for lesion segmentation and classification of MS and NMOSD","volume":"18","year":"2024","journal-title":"Front. Neurosci"},{"key":"2026050819500984000_2026.03.04.26347460v2.42","doi-asserted-by":"crossref","first-page":"105420","DOI":"10.1016\/j.msard.2023.105420","article-title":"Differentiating multiple sclerosis from non- specific white matter changes using a convolutional neural network image classification model","volume":"82","year":"2024","journal-title":"Mult. Scler. Relat. Disord"},{"key":"2026050819500984000_2026.03.04.26347460v2.43","doi-asserted-by":"crossref","first-page":"897959","DOI":"10.3389\/fimmu.2022.897959","article-title":"Transformer-based deep-learning algorithm for discriminating demyelinating diseases of the central nervous system with neuroimaging","volume":"13","year":"2022","journal-title":"Front. Immunol"},{"key":"2026050819500984000_2026.03.04.26347460v2.44","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1097\/RLI.0000000000000735","article-title":"Deep learning on conventional magnetic resonance imaging improves the diagnosis of multiple sclerosis mimics","volume":"56","year":"2021","journal-title":"Invest. Radiol"},{"key":"2026050819500984000_2026.03.04.26347460v2.45","doi-asserted-by":"crossref","first-page":"12104","DOI":"10.1038\/s41598-024-61876-9","article-title":"AI- based model for automatic identification of multiple sclerosis based on enhanced sea-horse optimizer and MRI scans","volume":"14","year":"2024","journal-title":"Sci. Rep"},{"key":"2026050819500984000_2026.03.04.26347460v2.46","doi-asserted-by":"crossref","first-page":"609468","DOI":"10.3389\/fnins.2020.609468","article-title":"Investigation of deep-learning-driven identification of multiple sclerosis patients based on susceptibility- weighted images using relevance analysis","volume":"14","year":"2020","journal-title":"Front. Neurosci"},{"key":"2026050819500984000_2026.03.04.26347460v2.47","doi-asserted-by":"crossref","first-page":"e214075","DOI":"10.1212\/WNL.0000000000214075","article-title":"Deep learning modeling to differentiate multiple sclerosis from MOG antibody-associated disease","volume":"105","year":"2025","journal-title":"Neurology"},{"key":"2026050819500984000_2026.03.04.26347460v2.48","doi-asserted-by":"publisher","DOI":"10.1177\/1352458512471874"},{"key":"2026050819500984000_2026.03.04.26347460v2.49","first-page":"e784","article-title":"Diagnostic performance of adding the optic nerve region assessed by optical coherence tomography to the diagnostic criteria for multiple sclerosis","volume":"101","year":"2023","journal-title":"Neurology"},{"key":"2026050819500984000_2026.03.04.26347460v2.50","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012799"},{"key":"2026050819500984000_2026.03.04.26347460v2.51","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30470-2"},{"key":"2026050819500984000_2026.03.04.26347460v2.52","doi-asserted-by":"publisher","DOI":"10.1002\/ana.22366"},{"key":"2026050819500984000_2026.03.04.26347460v2.53","doi-asserted-by":"crossref","first-page":"e210049","DOI":"10.1212\/WNL.0000000000210049","article-title":"Ocrelizumab in early-stage relapsing-remitting multiple sclerosis: The phase IIIb ENSEMBLE 4-year, single-arm, open-label trial","volume":"103","year":"2024","journal-title":"Neurology"},{"key":"2026050819500984000_2026.03.04.26347460v2.54","doi-asserted-by":"crossref","unstructured":"Chen, J. et al. Optimization and validation of the DESIGNER preprocessing pipeline for clinical diffusion MRI in white matter aging. Imaging Neurosci. (Camb.) 2, (2024).","DOI":"10.1162\/imag_a_00125"},{"key":"2026050819500984000_2026.03.04.26347460v2.55","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(03)00336-7"},{"key":"2026050819500984000_2026.03.04.26347460v2.56","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908"},{"key":"2026050819500984000_2026.03.04.26347460v2.57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2018.07.066"},{"key":"2026050819500984000_2026.03.04.26347460v2.58","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28830"},{"key":"2026050819500984000_2026.03.04.26347460v2.59","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.1076"},{"key":"2026050819500984000_2026.03.04.26347460v2.60","unstructured":"Ilse, M. , Tomczak, J. & Welling, M. Attention-based Deep Multiple Instance Learning. in Proceedings of the 35th International Conference on Machine Learning (eds Dy, J. & Krause, A.) vol. 80 2127\u20132136 (PMLR, 10--15 Jul 2018)."},{"key":"2026050819500984000_2026.03.04.26347460v2.61","unstructured":"Guo, C. , Pleiss, G. , Sun, Y. & Weinberger, K. Q . On calibration of modern neural networks. arXiv [cs.LG] (2017)."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.04.26347460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T02:50:28Z","timestamp":1778295028000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.03.04.26347460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":61,"URL":"https:\/\/doi.org\/10.64898\/2026.03.04.26347460","relation":{},"subject":[],"published":{"date-parts":[[2026,3,10]]},"subtype":"preprint"}}