{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T10:50:15Z","timestamp":1791456615537,"version":"4.3.4"},"reference-count":51,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["IZKSZ3_218590"],"award-info":[{"award-number":["IZKSZ3_218590"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008464","name":"EMDO Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008464","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008494","name":"Vontobel-Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008494","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Norges Forskningsr\u00e5d","doi-asserted-by":"publisher","award":["302624"],"award-info":[{"award-number":["302624"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Magnetic Resonance Imaging"],"published-print":{"date-parts":[[2026,7]]},"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n Intravoxel incoherent motion (IVIM) analysis of diffusion\u2010weighted MRI (DWI) provides microvascular perfusion and diffusion information. However, parameter estimation is limited by noise sensitivity, variability across fitting methods, and lack of standardization. Deep\u2010learning (DL)\u2013based approaches, particularly spatially\u2010aware transformers, may improve robustness, but their clinical utility remains unexplored.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n To evaluate conventional, Bayesian, and DL\u2013based IVIM fitting methods in glioma patients, focusing on tumor grading accuracy.<\/jats:p>\n <\/jats:sec>\n \n Study Type<\/jats:title>\n Retrospective.<\/jats:p>\n <\/jats:sec>\n \n Population<\/jats:title>\n Fractal\u2010noise\u2010based simulations and preoperative DWI from 20 glioma patients (5 Grade\u20102, 3 Grade\u20103, 12 Grade\u20104).<\/jats:p>\n <\/jats:sec>\n \n Sequence<\/jats:title>\n \n Spin\u2010echo echo\u2010planar DWI, 16\n b<\/jats:italic>\n values (0\u2013900\u2009s\/mm\n 2<\/jats:sup>\n ), three orthogonal directions, 3\u2009T.\n <\/jats:p>\n <\/jats:sec>\n \n Assessment<\/jats:title>\n \n IVIM parameter maps were compared across least squares (LSQ), segmented (SEG), Bayesian shrinkage (BSP), and spatial\u2010homogeneity (FBM) priors, and DL\u2013based methods, including IVIM\u2010NET, novel spatially\u2010aware transformers (NATTEN\u201017), and a refined version (SA\u201017). Simulation accuracy was evaluated using median absolute percentage error (MDAPE) and bias using median percentage error. In\u00a0vivo data were visually assessed by the authors for noise suppression and structural preservation. Whole\u2010tumor diffusion coefficient (\n D<\/jats:italic>\n ), pseudo\u2010diffusion coefficient (\n D<\/jats:italic>\n *), and signal fraction (\n f<\/jats:italic>\n ) values were evaluated across tumor grades and for differentiating Grade\u20104 from Grade\u20102\/3 tumors.\n <\/jats:p>\n <\/jats:sec>\n \n Statistical Tests<\/jats:title>\n \n Mann\u2013Whitney\n U<\/jats:italic>\n tests for group comparisons; tumor grading performance using receiver operating characteristic\u2013area under the curve (ROC\u2010AUC), and pairwise AUC differences using the DeLong test. Significance:\n p<\/jats:italic>\n \u2009<\u20090.05.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Transformer\u2010based methods achieved superior simulation accuracy, with significantly lower MDAPE for\n f<\/jats:italic>\n and\n D<\/jats:italic>\n * than all other approaches: NATTEN\u201017 (5.91%, 13.31%), SA\u201017 (7.73%, 13.66%), LSQ (21.95%, 54.34%), SEG (17.10%, 21.27%), BSP (12.35%, 22.79%), FBM (16.32%, 20.67%). In\u00a0vivo, they provided superior visual quality and tumor delineation in\n f<\/jats:italic>\n and\n D<\/jats:italic>\n * maps, producing seemingly denoised versions of LSQ, while preserving tumor heterogeneity. The spatially\u2010aware transformers yielded consistently the highest ROC\u2010AUC values, particularly for\n D<\/jats:italic>\n * (SA\u201017: 0.78), significantly outperforming LSQ (0.62), SEG (0.58), FBM (0.62), and IVIM\u2010NET (0.71).\n <\/jats:p>\n <\/jats:sec>\n \n Data Conclusion<\/jats:title>\n Transformer\u2010based model fitting has the potential to provide clinically valuable IVIM parameter estimates and improved tumor grading accuracy.<\/jats:p>\n <\/jats:sec>\n \n Evidence Level<\/jats:title>\n 3.<\/jats:p>\n <\/jats:sec>\n \n Technical Efficacy<\/jats:title>\n Stage 2.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jmri.70301","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:04:51Z","timestamp":1774933491000},"page":"184-200","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Comparative Study of\n IVIM<\/scp>\n \u2010\n MRI<\/scp>\n Fitting Techniques in Glioma Grading: Conventional, Bayesian, and Voxel\u2010Wise and Spatially\u2010Aware Deep Learning Approaches"],"prefix":"10.1002","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7340-8256","authenticated-orcid":false,"given":"Misha P. T.","family":"Kaandorp","sequence":"first","affiliation":[{"name":"Center for MR Research University Children's Hospital Zurich Zurich Switzerland"},{"name":"University of Zurich Zurich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6291-9889","authenticated-orcid":false,"given":"Andras","family":"Jakab","sequence":"additional","affiliation":[{"name":"Center for MR Research University Children's Hospital Zurich Zurich Switzerland"},{"name":"University of Zurich Zurich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3803-6602","authenticated-orcid":false,"given":"Christian","family":"Federau","sequence":"additional","affiliation":[{"name":"University of Zurich Zurich Switzerland"},{"name":"AI Medical AG Zollikon Switzerland"},{"name":"Kyoto Prefectural University of Medicine Kyoto Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2602-0758","authenticated-orcid":false,"given":"Peter T.","family":"While","sequence":"additional","affiliation":[{"name":"Department of Radiology and Nuclear Medicine St. Olav's University Hospital Trondheim Norway"},{"name":"Department of Circulation and Medical Imaging NTNU\u2014Norwegian University of Science and Technology Trondheim Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.161.2.3763909"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1593\/neo.81328"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.168.2.3393671"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.30042"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0194590"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26169"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.24799"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26598"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26772"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429427275-23"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.1910230113"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1034\/j.1600\u20100455.2001.042002123.x"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24649"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2012.12.001"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102144"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29628"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103414"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28852"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27910"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28989"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac9a1f"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103445"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17583"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3833"},{"key":"e_1_2_9_26_1","volume-title":"Deep Learning Diffusion Parameters From Magnetic Resonance Imaging: An Odyssey of Deep Learning IVIM Parameter Estimation","author":"Kaandorp M. P. T.","year":"2024"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/325165.325247"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A3686"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.3223"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noab106"},{"key":"e_1_2_9_31_1","unstructured":"D. A.Clevert T.Unterthiner andS.Hochreiter \u201cFast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) \u201d4th International Conference on Learning Representations ICLR 2016\u2014Conference Track Proceedings 2016 1\u201314."},{"key":"e_1_2_9_32_1","unstructured":"D. P.KingmaandJ. L.Ba \u201cAdam: A Method for Stochastic Optimization \u201d3rd International Conference on Learning Representations ICLR 2015\u2014Conference Track Proceedings 2015 1\u201315."},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"A.Hassani S.Walton J.Li S.Li andH.Shi \u201cNeighborhood Attention Transformer \u201dProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2023 6185\u20136194 http:\/\/arxiv.org\/abs\/2209.15001.","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"e_1_2_9_34_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et\u00a0al. \u201cAttention Is All You Need \u201dAdvances in Neural Information Processing Systems 2017 5999\u20136009."},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"W.Chen F. W.Samuelson B. D.Gallas L.Kang B.Sahiner andN.Petrick \u201cOn the Assessment of the Added Value of New Predictive Biomarkers \u201d2013 http:\/\/www.biomedcentral.com\/1471\u20102288\/13\/98DEBATE.","DOI":"10.1186\/1471-2288-13-98"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29261"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010024\u201003113\u20104"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109256"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.70278"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106495"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1177\/0962280214537344"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10334\u2010018\u20100697\u20105"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep07208"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.25191"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.191.1.8134596"},{"issue":"10","key":"e_1_2_9_46_1","first-page":"1989","article-title":"Glioma Grading: Sensitivity, Specificity, and Predictive Values of Perfusion MR Imaging and Proton MR Spectroscopic Imaging Compared With Conventional MR Imaging","volume":"24","author":"Law M.","year":"2003","journal-title":"American Journal of Neuroradiology"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2472070898"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pharmthera.2015.06.006"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103768"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16031"},{"key":"e_1_2_9_51_1","doi-asserted-by":"crossref","unstructured":"N.Kertes Y.Zaffrani\u2010Reznikov O.Afacan S.Kurugol S. K.Warfield andM.Freiman \u201cIVIM\u2010Morph: Motion\u2010Compensated Quantitative Intra\u2010Voxel Incoherent Motion (IVIM) Analysis for Functional Fetal Lung Maturity Assessment From Diffusion\u2010Weighted MRI Data \u201d2024 arXiv.","DOI":"10.1016\/j.media.2024.103445"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/nbm.4774"}],"container-title":["Journal of Magnetic Resonance Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70301","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jmri.70301","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jmri.70301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T04:02:37Z","timestamp":1781150557000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jmri.70301"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/jmri.70301"],"URL":"https:\/\/doi.org\/10.1002\/jmri.70301","archive":["Portico"],"relation":{},"ISSN":["1053-1807","1522-2586"],"issn-type":[{"value":"1053-1807","type":"print"},{"value":"1522-2586","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"2025-11-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}