{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:19:33Z","timestamp":1784819973744,"version":"3.55.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["320030-227901"],"award-info":[{"award-number":["320030-227901"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["PP00P3_206151"],"award-info":[{"award-number":["PP00P3_206151"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Quantitative susceptibility mapping (QSM) has emerged as a promising paraclinical tool in multiple sclerosis (MS). This retrospective pilot study aims to evaluate whether a recently proposed deep learning-assisted, k-space-operating reconstruction, denoising and super-resolution technique (DLR) applied on 3D-echo-planar-imaging (3DEPI) protocols, has the potential to improve the quality and clinical utility of QSM in MS, at 3T. Secondarily, we assess whether applying DLR vs. a conventional reconstruction (CR) can improve the quality of QSM based on noise-susceptible, fast 3DEPI protocols.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>3T MRI 3DEPI-data were acquired on seven MS patients and offline-reconstructed using CR and DLR. <jats:italic>A sample size of 433 lesions was identified, based on<\/jats:italic> FLAIR segmentation. Two experts, independently and method-blinded, rated lesion-wise the CR- and DLR-3DEPI-derived QSM, assessing the confidence in identifying paramagnetic rim lesions (PRLs), central vein sign (CVS), QSM hyper\/isointense lesions and image quality. Gradient-recalled-echo (GRE), 2- and 1-average 3DEPI (acquisition time: 7:02, 3:44, and 1:56 min, respectively) from a healthy individual were offline-reconstructed using CR and DLR. Derived QSM maps were compared visually and quantitatively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Deep learning reconstruction-3DEPI-based QSM was rated significantly higher for the confidence in identification of the MS-specific biomarkers (hyper\/isointense lesions: <jats:italic>P<\/jats:italic> &amp;lt; 0.001, CVS: <jats:italic>P<\/jats:italic> = 0.01) and overall image quality (<jats:italic>P<\/jats:italic> &amp;lt; 0.001), compared to CR-3DEPI-based. Inter-method agreement was high for both raters (Cohen\u2019s \u03ba = 0.98\/0.92), suggesting that DLR improves the quality without changing the rater\u2019s perception of the individual QSM-related clinical findings. Additionally, QSM derived from fast DLR-3DEPI with a fourfold acquisition-time reduction compared to GRE, exhibited excellent visual and quantitative consistency with GRE-based QSM.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our results constitute a first demonstration of the enhanced quality and clinical utility of the DLR-3DEPI-based QSM in MS.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2025.1544376","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:35:06Z","timestamp":1752644106000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A pilot study assessing the clinical utility of deep learning-reconstructed 3D-echo-planar-imaging-based quantitative susceptibility mapping in multiple sclerosis"],"prefix":"10.3389","volume":"19","author":[{"given":"Dimitrios G.","family":"Gkotsoulias","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Weigel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Cagol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina de Oliveira Soares","family":"Siebenborn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Ruberte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Pfeuffer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina","family":"Granziera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1001\/jamaneurol.2019.2399","article-title":"Association of chronic active multiple sclerosis lesions with disability in vivo.","volume":"76","author":"Absinta","year":"2019","journal-title":"JAMA Neurol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1097\/RLI.0000000000000825","article-title":"Analysis of a deep learning-based superresolution algorithm tailored to partial fourier gradient echo sequences of the abdomen at 1.5 T: Reduction of breath-hold time and improvement of image quality.","volume":"57","author":"Afat","year":"2022","journal-title":"Invest. Radiol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1097\/RLI.0000000000000769","article-title":"Deep learning-based superresolution reconstruction for upper abdominal magnetic resonance imaging: An analysis of image quality, diagnostic confidence, and lesion conspicuity.","volume":"56","author":"Almansour","year":"2021","journal-title":"Invest. Radiol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1093\/brain\/awae013","article-title":"Imaging chronic active lesions in multiple sclerosis: A consensus statement.","volume":"147","author":"Bagnato","year":"2024","journal-title":"Brain"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.1109\/TMI.2016.2549918","article-title":"Reconstruction of 7T-Like Images From 3T MRI.","volume":"35","author":"Bahrami","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B6","author":"Behl","year":"2021","journal-title":"Deep resolve \u2013 mobilizing the power of networks (White paper) MAGNETOM flash (78):1\/2021."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e207768","DOI":"10.1212\/WNL.0000000000207768","article-title":"Association of spinal cord atrophy and brain paramagnetic rim lesions with progression independent of relapse activity in people with MS.","volume":"102","author":"Cagol","year":"","journal-title":"Neurology"},{"key":"B8","doi-asserted-by":"publisher","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","author":"Cagol","year":"","journal-title":"JAMA Neurol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.3390\/diagnostics10121025","article-title":"The use of the central vein sign in the diagnosis of multiple sclerosis: A systematic review and meta-analysis.","volume":"10","author":"Castellaro","year":"2020","journal-title":"Diagnostics (Basel)"},{"key":"B10","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.diii.2022.06.006","article-title":"Deep learning-based super-resolution gradient echo imaging of the pancreas: Improvement of image quality and reduction of acquisition time.","volume":"104","author":"Chaika","year":"2023","journal-title":"Diagn. Interv. Imaging"},{"key":"B11","doi-asserted-by":"publisher","first-page":"117433","DOI":"10.1016\/j.neuroimage.2020.117433","article-title":"Associations of quantitative susceptibility mapping with Alzheimer\u2019s disease clinical and imaging markers.","volume":"224","author":"Cogswell","year":"2021","journal-title":"Neuroimage"},{"key":"B12","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1002\/nbm.3569","article-title":"Overview of quantitative susceptibility mapping.","volume":"30","author":"Deistung","year":"2017","journal-title":"NMR Biomed."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.3390\/tomography8030127","article-title":"Magnetic susceptibility source separation solely from gradient echo data: Histological validation.","volume":"8","author":"Dimov","year":"2022","journal-title":"Tomography"},{"key":"B14","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1002\/mp.14006","article-title":"Reconstruction of multicontrast MR images through deep learning.","volume":"47","author":"Do","year":"2020","journal-title":"Med. Phys."},{"key":"B15","doi-asserted-by":"publisher","first-page":"3383","DOI":"10.1002\/mrm.28668","article-title":"Bulk volume susceptibility difference between deoxyhemoglobin and oxyhemoglobin for HbA and HbS: A comparative study.","volume":"85","author":"Eldeniz","year":"2021","journal-title":"Magn. Reson. Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1002\/mrm.1910030217","article-title":"Rapid NMR imaging of dynamic processes using the FLASH technique.","volume":"3","author":"Frahm","year":"1986","journal-title":"Magn. Reson. Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1002\/acn3.51338","article-title":"QSM is an imaging biomarker for chronic glial activation in multiple sclerosis lesions.","volume":"8","author":"Gillen","year":"2021","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.mri.2024.04.020","article-title":"Chaos and COSMOS-Considerations on QSM methods with multiple and single orientations and effects from local anisotropy.","volume":"110","author":"Gkotsoulias","year":"2024","journal-title":"Magn. Reson. Imaging"},{"key":"B19","doi-asserted-by":"publisher","first-page":"fcaf104","DOI":"10.1093\/braincomms\/fcaf104","article-title":"Abnormalities of iron homeostasis and the dopaminergic system in Tourette syndrome revealed by 7T MRI and PET.","volume":"7","author":"Gkotsoulias","year":"2025","journal-title":"Brain Commun."},{"key":"B20","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1002\/jmri.25970","article-title":"Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI.","volume":"48","author":"Gong","year":"2018","journal-title":"J. Magn. Reson. Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1093\/brain\/awab029","article-title":"Quantitative magnetic resonance imaging towards clinical application in multiple sclerosis.","volume":"144","author":"Granziera","year":"2021","journal-title":"Brain"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","article-title":"Learning a variational network for reconstruction of accelerated MRI data.","volume":"79","author":"Hammernik","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"B23","first-page":"10","author":"Hammernik","year":"2019","journal-title":"Deep learning for parallel MRI reconstruction. MAGNETOM Flash (75):4\/2019."},{"key":"B24","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1111\/jon.12987","article-title":"Quantitative susceptibility mapping versus phase imaging to identify multiple sclerosis iron rim lesions with demyelination.","volume":"32","author":"Huang","year":"2022","journal-title":"J. Neuroimaging"},{"key":"B25","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.neuroimage.2011.09.015","article-title":"FSL.","volume":"62","author":"Jenkinson","year":"2012","journal-title":"Neuroimage"},{"key":"B26","doi-asserted-by":"publisher","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":"B27","article-title":"Adam: A method for stochastic optimization.","author":"Kingma","year":"2014","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e220133","DOI":"10.1148\/rg.220133","article-title":"Clinical impact of deep learning reconstruction in MRI.","volume":"43","author":"Kiryu","year":"2023","journal-title":"Radiographics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"102335","DOI":"10.1016\/j.nicl.2020.102335","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 Clin."},{"key":"B30","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1016\/j.neuroimage.2015.02.041","article-title":"Fast quantitative susceptibility mapping using 3D EPI and total generalized variation.","volume":"111","author":"Langkammer","year":"2015","journal-title":"Neuroimage"},{"key":"B31","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1148\/radiol.12120707","article-title":"Quantitative susceptibility mapping in multiple sclerosis.","volume":"267","author":"Langkammer","year":"2013","journal-title":"Radiology"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1002\/mrm.26830","article-title":"Quantitative susceptibility mapping: Report from the 2016 reconstruction challenge.","volume":"79","author":"Langkammer","year":"","journal-title":"Magn. Reson. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"e0162460","DOI":"10.1371\/journal.pone.0162460","article-title":"Quantitative susceptibility mapping in Parkinson\u2019s disease.","volume":"11","author":"Langkammer","year":"","journal-title":"PLoS One"},{"key":"B34","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1111\/jon.12938","article-title":"The central vein sign in multiple sclerosis lesions: Susceptibility relaxation optimization from a routine MRI multiecho gradient echo sequence.","volume":"32","author":"Li","year":"2022","journal-title":"J. Neuroimaging"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1016\/j.neuroimage.2010.11.088","article-title":"Quantitative susceptibility mapping of human brain reflects spatial variation in tissue composition.","volume":"55","author":"Li","year":"2011","journal-title":"Neuroimage"},{"key":"B36","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1002\/jmri.24976","article-title":"Magnetic susceptibility contrast variations in multiple sclerosis lesions.","volume":"43","author":"Li","year":"2016","journal-title":"J. Magn. Reson. Imaging"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.3390\/jcm12051916","article-title":"Diagnostic image quality of a low-field (0.55T) knee MRI protocol using deep learning image reconstruction compared with a standard (1.5T) knee MRI protocol.","volume":"12","author":"Lopez Schmidt","year":"2023","journal-title":"J. Clin. Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1002\/ana.25146","article-title":"Central vein sign differentiates Multiple Sclerosis from central nervous system inflammatory vasculopathies.","volume":"83","author":"Maggi","year":"2018","journal-title":"Ann. Neurol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1080\/14737175.2022.2143265","article-title":"What is the potential of paramagnetic rim lesions as diagnostic indicators in multiple sclerosis?","volume":"22","author":"Martire","year":"2022","journal-title":"Expert Rev. Neurother."},{"key":"B40","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/j.tins.2019.03.009","article-title":"Iron, myelin, and the brain: Neuroimaging meets neurobiology.","volume":"42","author":"M\u00f6ller","year":"2019","journal-title":"Trends Neurosci."},{"key":"B41","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Proceedings of the 33rd conference on neural information processing systems"},{"key":"B42","author":"Pfeuffer","year":"2024","journal-title":"Advances in susceptibility-weighted imaging (SWI) and quantitative susceptibility mapping (QSM), MAGNETOM Flash (87):2\/2024."},{"key":"B43","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1097\/WCO.0000000000000946","article-title":"Central vein sign and iron rim in multiple sclerosis: Ready for clinical use?","volume":"34","author":"Preziosa","year":"2021","journal-title":"Curr. Opin. Neurol."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1002\/mrm.30006","article-title":"Recommended implementation of quantitative susceptibility mapping for clinical research in the brain: A consensus of the ISMRM electro-magnetic tissue properties study group.","volume":"91","author":"Bilgic","year":"2024","journal-title":"Magn. Reson. Med."},{"key":"B45","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1002\/ana.26441","article-title":"A new advanced MRI biomarker for remyelinated lesions in multiple sclerosis.","volume":"92","author":"Rahmanzadeh","year":"2022","journal-title":"Ann. Neurol."},{"key":"B46","doi-asserted-by":"publisher","first-page":"e210059","DOI":"10.1148\/ryai.210059","article-title":"Clinical assessment of deep learning-based super-resolution for 3D volumetric brain MRI.","volume":"4","author":"Rudie","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"B47","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1038\/nrneurol.2016.166","article-title":"The central vein sign and its clinical evaluation for the diagnosis of multiple sclerosis: A consensus statement from the North American imaging in multiple sclerosis cooperative.","volume":"12","author":"Sati","year":"2016","journal-title":"Nat. Rev. Neurol."},{"key":"B48","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1177\/1352458514525868","article-title":"Rapid, high-resolution, whole-brain, susceptibility-based MRI of multiple sclerosis.","volume":"20","author":"Sati","year":"2014","journal-title":"Mult. Scler."},{"key":"B49","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.zemedi.2015.10.002","article-title":"Foundations of MRI phase imaging and processing for quantitative susceptibility mapping (QSM).","volume":"26","author":"Schweser","year":"2016","journal-title":"Z. Med. Phys."},{"key":"B50","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1038\/s41398-024-02862-7","article-title":"Alterations in subcortical magnetic susceptibility and disease-specific relationship with brain volume in major depressive disorder and schizophrenia.","volume":"14","author":"Shibukawa","year":"2024","journal-title":"Transl. Psychiatry"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1002\/mrm.29048","article-title":"QSMxT: Robust masking and artifact reduction for quantitative susceptibility mapping.","volume":"87","author":"Stewart","year":"2022","journal-title":"Magn. Reson. Med."},{"key":"B52","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1002\/mrm.30101","article-title":"Three-dimensional EPI with shot-selective CAIPIRIHANA for rapid high-resolution quantitative susceptibility mapping at 3 T.","volume":"92","author":"Tourell","year":"2024","journal-title":"Magn. Reson. Med."},{"key":"B53","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1002\/jmri.25693","article-title":"Clinical quantitative susceptibility mapping (QSM): Biometal imaging and its emerging roles in patient care.","volume":"46","author":"Wang","year":"2017","journal-title":"J. Magn. Reson. Imaging"},{"key":"B54","doi-asserted-by":"publisher","first-page":"987","DOI":"10.3174\/ajnr.A6071","article-title":"Quantitative susceptibility mapping of time-dependent susceptibility changes in multiple sclerosis lesions.","volume":"40","author":"Zhang","year":"2019","journal-title":"AJNR Am. J. Neuroradiol."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1544376\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:35:08Z","timestamp":1752644108000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1544376\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":54,"alternative-id":["10.3389\/fnins.2025.1544376"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1544376","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"article-number":"1544376"}}