{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T13:14:25Z","timestamp":1789478065318,"version":"build-2803163510"},"reference-count":59,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100009882","name":"Regione Lombardia","doi-asserted-by":"publisher","award":["1739635"],"award-info":[{"award-number":["1739635"]}],"id":[{"id":"10.13039\/501100009882","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["NMR in Biomedicine"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion\u2010weighted MRI remains challenging due to the ill\u2010posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion compartment. In this work, we propose a probabilistic deep learning framework based on deep ensembles (DEs) of mixture density networks (MDNs), enabling estimation of total predictive uncertainty and decomposition into aleatoric (AU) and epistemic (EU) components. The method was benchmarked against nonprobabilistic neural networks, a Bayesian fitting approach, and a probabilistic network with single Gaussian parametrization. Supervised training was performed on synthetic data, and evaluation was conducted on both simulated and in\u00a0vivo brain mouse dataset. The reliability of the quantified uncertainties was assessed using calibration curves, output distribution sharpness, and the continuous ranked probability score (CRPS). MDNs produced more calibrated and sharper predictive distributions for the diffusion coefficient () and the perfusion fraction () parameters, although slight overconfidence was observed in the pseudodiffusion coefficient (). The robust coefficient of variation (RCV) indicated smoother in\u00a0vivo estimates for  with MDNs compared with Gaussian model. Despite the training data covering the expected physiological range, elevated EU in\u00a0vivo suggests a mismatch with real acquisition conditions, highlighting the importance of incorporating EU, which was allowed by DE. Overall, we present a comprehensive framework for IVIM fitting with uncertainty quantification, which enables the identification and interpretation of unreliable estimates. The proposed approach can also be adopted for fitting other physical models through appropriate architectural and simulation adjustments.<\/jats:p>","DOI":"10.1002\/nbm.70227","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:53:43Z","timestamp":1768892023000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Comprehensive Framework for Uncertainty Quantification of Voxel\u2010Wise Supervised Deep Learning Models in IVIM MRI"],"prefix":"10.1002","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6800-5341","authenticated-orcid":false,"given":"Nicola","family":"Casali","sequence":"first","affiliation":[{"name":"Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato Consiglio Nazionale delle Ricerche  Milan Italy"},{"name":"Politecnico di Milano  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0838-9826","authenticated-orcid":false,"given":"Alessandro","family":"Brusaferri","sequence":"additional","affiliation":[{"name":"Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato Consiglio Nazionale delle Ricerche  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2978-1704","authenticated-orcid":false,"given":"Giuseppe","family":"Baselli","sequence":"additional","affiliation":[{"name":"Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato Consiglio Nazionale delle Ricerche  Milan Italy"},{"name":"Politecnico di Milano  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3598-6263","authenticated-orcid":false,"given":"Stefano","family":"Fumagalli","sequence":"additional","affiliation":[{"name":"Department of Acute Brain and Cardiovascular Injury Istituto di Ricerche Farmacologiche Mario Negri IRCCS  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5995-2992","authenticated-orcid":false,"given":"Edoardo","family":"Micotti","sequence":"additional","affiliation":[{"name":"Department of Neuroscience Istituto di Ricerche Farmacologiche Mario Negri IRCCS  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5374-3914","authenticated-orcid":false,"given":"Gianluigi","family":"Forloni","sequence":"additional","affiliation":[{"name":"Department of Neuroscience Istituto di Ricerche Farmacologiche Mario Negri IRCCS  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-2345","authenticated-orcid":false,"given":"Riaz","family":"Hussain","sequence":"additional","affiliation":[{"name":"Department of Neuroscience Istituto di Ricerche Farmacologiche Mario Negri IRCCS  Milan Italy"},{"name":"Division of Pulmonary Medicine Cincinnati Children\u2019s Hospital Medical Center  Cincinnati Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6341-1304","authenticated-orcid":false,"given":"Giovanna","family":"Rizzo","sequence":"additional","affiliation":[{"name":"Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato Consiglio Nazionale delle Ricerche  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3358-7111","authenticated-orcid":false,"given":"Alfonso","family":"Mastropietro","sequence":"additional","affiliation":[{"name":"Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato Consiglio Nazionale delle Ricerche  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1910270116"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.168.2.3393671"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.12.062"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16821"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.27875"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3245"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3922"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3780"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1097\/RLI.0000000000000040"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27879"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25535"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26598"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2025.104978"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3833"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27910"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28852"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac9a1f"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28989"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16031"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17825"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17583"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29628"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4774"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103414"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecosta.2021.07.006"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2008.922191"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21646"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107441"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103223"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102830"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2019.8759391"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-95841-0_17"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.101069.3"},{"issue":"57","key":"e_1_2_11_35_1","first-page":"1","article-title":"Normalizing Flows for Probabilistic Modeling and Inference","volume":"22","author":"Papamakarios G.","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103580"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230446"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103537"},{"key":"e_1_2_11_39_1","first-page":"5580","article-title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","volume":"30","author":"Kendall A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_40_1","unstructured":"C. M.Bishop \u201cMixture Density Networks \u201d (1994)."},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-66535-6_17"},{"key":"e_1_2_11_43_1","first-page":"6405","article-title":"Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles","volume":"30","author":"Lakshminarayanan B.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_44_1","first-page":"1184","volume-title":"International Conference on Machine Learning","author":"Depeweg S.","year":"2018"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26783"},{"key":"e_1_2_11_46_1","unstructured":"D. P.Kingma \u201cAdam: A Method for Stochastic Optimization \u201d preprint arXiv January 30 2017 https:\/\/doi.org\/10.48550\/arXiv.1412.6980."},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/02664763.2020.1808599"},{"key":"e_1_2_11_48_1","first-page":"2796","volume-title":"International Conference on Machine Learning","author":"Kuleshov V.","year":"2018"},{"key":"e_1_2_11_49_1","unstructured":"J.Yao W.Pan S.Ghosh andF.Doshi\u2010Velez \u201cQuality of Uncertainty Quantification for Bayesian Neural Network Inference \u201d preprint arXiv June 24 2019 https:\/\/doi.org\/10.48550\/arXiv.1906.09686."},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106203"},{"key":"e_1_2_11_51_1","first-page":"393","volume-title":"Medical Imaging With Deep Learning","author":"Laves M. H.","year":"2020"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2007.00587.x"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214506000001437"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2162110"},{"key":"e_1_2_11_55_1","unstructured":"L.L\u00f3pez S.Elsharief D. A.Jorf F.Darwish C.Ma andF. E.Shamout \u201cUncertainty Quantification for Machine Learning in Healthcare: A Survey \u201d preprint arXiv May 4 2025 https:\/\/doi.org\/10.48550\/arXiv.2505.02874."},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.70136"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29014"},{"key":"e_1_2_11_58_1","first-page":"2282","volume-title":"Uncertainty in Artificial Intelligence","author":"Wimmer L.","year":"2023"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-015-3655-x"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06248-y"}],"container-title":["NMR in Biomedicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nbm.70227","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/nbm.70227","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/nbm.70227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T17:53:43Z","timestamp":1772992423000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/nbm.70227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":59,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1002\/nbm.70227"],"URL":"https:\/\/doi.org\/10.1002\/nbm.70227","archive":["Portico"],"relation":{},"ISSN":["0952-3480","1099-1492"],"issn-type":[{"value":"0952-3480","type":"print"},{"value":"1099-1492","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]},"assertion":[{"value":"2025-08-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70227"}}