{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T13:04:39Z","timestamp":1771074279099,"version":"3.50.1"},"posted":{"date-parts":[[2026,2,12]]},"group-title":"Neurology","reference-count":50,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:00:00Z","timestamp":1770854400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,2,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>MRI plays an essential role in diagnosing and monitoring neurological diseases. Conventional protocols rely on multiple sequences to obtain complementary contrasts, increasing scan time, cost, and tolerability. Generating multiple contrasts from a single acquisition may streamline workflow while maintaining clinical utility.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>Train attention-based convolutional neural networks (ACNNs) to generate clinical-quality FLAIR, MPRAGE, R2*, and derived contrasts from a single Gradient Echo Plural Contrast Imaging (GEPCI) acquisition, enabling multi-contrast imaging from one scan.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Study Type<\/jats:title>\n                  <jats:p>Retrospective.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Population<\/jats:title>\n                  <jats:p>43 MRI scans from individuals with multiple sclerosis (25\/18 F\/M, 49\u00b111 years old).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Field Strength\/Sequence<\/jats:title>\n                  <jats:p>3T MRI was used to obtain 3D GEPCI, MPRAGE, and FLAIR sequences.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Assessment<\/jats:title>\n                  <jats:p>Technical quality of the AI-generated contrasts was evaluated against directly acquired MRI images using structural similarity index (SSIM). Quantitative accuracy for R2* maps was evaluated using normalized root-mean-square error (NRMSE). Clinical image quality was assessed by expert physicians. Lesion volumes and counts were obtained using automated segmentation.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>AI-generated FLAIR and MPRAGE images achieved mean SSIM values of 0.923\u00b10.028 and 0.935\u00b10.022, respectively. The generated R2* maps achieved a mean SSIM of 0.996\u00b10.006, with quantitative accuracy reflected by an NRMSE of 0.031\u00b10.020. Physicians rated GEPCI-FLAIR images at 4.2 and GEPCI-MPRAGE images at 4.5 (on a 1-to-5 scale), both exceeding the clinically routine standard of 4.0. Lesion volume and count comparisons from automated segmentation showed strong agreement between AI-generated and ground-truth measurements (R\u00b2=0.988 and R\u00b2=0.933, respectively).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>AI-GEPCI generated multiple clinically relevant MRI contrasts from a single GEPCI acquisition with high similarity to corresponding acquired images. Radiological reviews and quantitative analyses supported the feasibility of producing high-quality, intrinsically co-registered multi-contrasts for comprehensive brain evaluation.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.02.11.26346017","type":"posted-content","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:15:17Z","timestamp":1770941717000},"source":"Crossref","is-referenced-by-count":0,"title":["AI-powered Gradient Echo Plural Contrast Imaging (AI-GEPCI) \u2013 a Comprehensive Multiparametric Neurological Protocol from a Single MRI Scan"],"prefix":"10.64898","author":[{"given":"Jeramy","family":"Lewis","sequence":"first","affiliation":[{"name":"Mallinckrodt Institute of Radiology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manu S.","family":"Goyal","sequence":"additional","affiliation":[{"name":"Mallinckrodt Institute of Radiology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory F.","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyang","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Electrical & Systems Engineering, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander L.","family":"Sukstanskii","sequence":"additional","affiliation":[{"name":"Mallinckrodt Institute of Radiology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satya V.V.N.","family":"Kothapalli","sequence":"additional","affiliation":[{"name":"Mallinckrodt Institute of Radiology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne H.","family":"Cross","sequence":"additional","affiliation":[{"name":"Department of Neurology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulugbek","family":"Kamilov","sequence":"additional","affiliation":[{"name":"Department of Electrical & Systems Engineering, Washington University in St. Louis,"},{"name":"Department of Computer Science & Engineering, Washington University in St. Louis, Washington University in St. Louis School of Medicine, 660 S. Euclid Ave, St. Louis, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2898-8797","authenticated-orcid":false,"given":"Dmitriy A.","family":"Yablonskiy","sequence":"additional","affiliation":[{"name":"Mallinckrodt Institute of Radiology, Washington University in St. Louis,"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026021404151347000_2026.02.11.26346017v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nature11971"},{"key":"2026021404151347000_2026.02.11.26346017v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.108"},{"key":"2026021404151347000_2026.02.11.26346017v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.116329"},{"key":"2026021404151347000_2026.02.11.26346017v1.4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.18073"},{"key":"2026021404151347000_2026.02.11.26346017v1.5","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25610"},{"key":"2026021404151347000_2026.02.11.26346017v1.6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1808121115"},{"key":"2026021404151347000_2026.02.11.26346017v1.7","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.24585"},{"key":"2026021404151347000_2026.02.11.26346017v1.8","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.25114"},{"key":"2026021404151347000_2026.02.11.26346017v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.12.026"},{"key":"2026021404151347000_2026.02.11.26346017v1.10","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-210503"},{"key":"2026021404151347000_2026.02.11.26346017v1.11","doi-asserted-by":"publisher","DOI":"10.1177\/1352458513495935"},{"key":"2026021404151347000_2026.02.11.26346017v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2015.08.003"},{"key":"2026021404151347000_2026.02.11.26346017v1.13","unstructured":"Xiang B , Jie W , Schmidt R , Yablonskiy D , Cross A. Quantitative assessment of multiple sclerosis tissue damage and partial repair in a biopsy proven demyelinating brain Lesion using gradient recalled echo imaging. Mult Scler J: SAGE PUBLICATIONS LTD 1 OLIVERS YARD, 55 CITY ROAD, LONDON EC1Y 1SP, ENGLAND, 2020; p. 93\u201394."},{"key":"2026021404151347000_2026.02.11.26346017v1.14","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26218"},{"key":"2026021404151347000_2026.02.11.26346017v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.schres.2015.10.004"},{"key":"2026021404151347000_2026.02.11.26346017v1.16","doi-asserted-by":"publisher","DOI":"10.1093\/milmed\/usy394"},{"key":"2026021404151347000_2026.02.11.26346017v1.17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03999"},{"key":"2026021404151347000_2026.02.11.26346017v1.18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.12120208"},{"key":"2026021404151347000_2026.02.11.26346017v1.19","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-018-0041-4"},{"key":"2026021404151347000_2026.02.11.26346017v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/1531-8249(200006)47:6<707::AID-ANA3>3.0.CO;2-Q"},{"key":"2026021404151347000_2026.02.11.26346017v1.21","doi-asserted-by":"publisher","DOI":"10.2174\/1381612822666161214153108"},{"issue":"13","key":"2026021404151347000_2026.02.11.26346017v1.22","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.3390\/diagnostics14131362","article-title":"Central Vein Sign and Paramagnetic Rim Lesions: Susceptibility Changes in Brain Tissues and Their Implications for the Study of Multiple Sclerosis Pathology","volume":"14","year":"2024","journal-title":"Diagnostics"},{"key":"2026021404151347000_2026.02.11.26346017v1.23","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a028969"},{"key":"2026021404151347000_2026.02.11.26346017v1.24","doi-asserted-by":"publisher","DOI":"10.1177\/13524585211073761"},{"key":"2026021404151347000_2026.02.11.26346017v1.25","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.21.26777"},{"key":"2026021404151347000_2026.02.11.26346017v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2022.103205"},{"key":"2026021404151347000_2026.02.11.26346017v1.27","doi-asserted-by":"publisher","DOI":"10.1177\/11795735221084842"},{"issue":"3_Suppl","key":"2026021404151347000_2026.02.11.26346017v1.28","first-page":"246","article-title":"Paramagnetic rim lesions are specific to multiple sclerosis: an international multicenter 3t mri study","volume":"26","year":"2020","journal-title":"Mult Scler J"},{"key":"2026021404151347000_2026.02.11.26346017v1.29","doi-asserted-by":"publisher","DOI":"10.1177\/13524585221118677"},{"key":"2026021404151347000_2026.02.11.26346017v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30470-2"},{"key":"2026021404151347000_2026.02.11.26346017v1.31","doi-asserted-by":"publisher","DOI":"10.1038\/nrneurol.2016.166"},{"key":"2026021404151347000_2026.02.11.26346017v1.32","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.10171"},{"key":"2026021404151347000_2026.02.11.26346017v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.09.015"},{"issue":"7","key":"2026021404151347000_2026.02.11.26346017v1.34","doi-asserted-by":"crossref","first-page":"3676","DOI":"10.3390\/app12073676","article-title":"MDA-Unet: A Multi-Scale Dilated Attention U-Net for Medical Image Segmentation","volume":"12","year":"2022","journal-title":"Applied Sciences"},{"key":"2026021404151347000_2026.02.11.26346017v1.35","unstructured":"Sang D , Chung T , Lan P , Dao H , Long D , Nguyen T . AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation, 2021."},{"key":"2026021404151347000_2026.02.11.26346017v1.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"2026021404151347000_2026.02.11.26346017v1.37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"2026021404151347000_2026.02.11.26346017v1.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.11.032"},{"key":"2026021404151347000_2026.02.11.26346017v1.39","unstructured":"Schmidt P. Bayesian inference for structured additive regression models for large-scale problems with applications to medical imaging. LMU Munich, 2017."},{"key":"2026021404151347000_2026.02.11.26346017v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118012"},{"key":"2026021404151347000_2026.02.11.26346017v1.41","doi-asserted-by":"publisher","DOI":"10.1109\/Tmi.2023.3261707"},{"key":"2026021404151347000_2026.02.11.26346017v1.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102457"},{"key":"2026021404151347000_2026.02.11.26346017v1.43","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2975344"},{"key":"2026021404151347000_2026.02.11.26346017v1.44","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14539"},{"key":"2026021404151347000_2026.02.11.26346017v1.45","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13530"},{"key":"2026021404151347000_2026.02.11.26346017v1.46","doi-asserted-by":"publisher","DOI":"10.1109\/Tmi.2017.2764326"},{"key":"2026021404151347000_2026.02.11.26346017v1.47","doi-asserted-by":"crossref","unstructured":"Li H , Paetzold JC , Sekuboyina A , et al. DiamondGAN: Unified Multi-modal Generative Adversarial Networks for MRI Sequences Synthesis. In: Shen D , Liu T , Peters TM , Staib LH , Essert C , Zhou S , Yap P- T , Khan A , eds. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019. Cham: Springer International Publishing, 2019; p. 795\u2013803.","DOI":"10.1007\/978-3-030-32251-9_87"},{"key":"2026021404151347000_2026.02.11.26346017v1.48","doi-asserted-by":"crossref","unstructured":"Yang H , Sun J , Yang L , Xu Z. A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation. In: de Bruijne M , Cattin PC , Cotin S , Padoy N , Speidel S , Zheng Y , Essert C , eds. Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021. Cham: Springer International Publishing, 2021; p. 127\u2013137.","DOI":"10.1007\/978-3-030-87199-4_12"},{"key":"2026021404151347000_2026.02.11.26346017v1.49","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-021-05384-2"},{"key":"2026021404151347000_2026.02.11.26346017v1.50","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-025-03547-8"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.02.11.26346017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T12:15:20Z","timestamp":1771071320000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.02.11.26346017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,12]]},"references-count":50,"URL":"https:\/\/doi.org\/10.64898\/2026.02.11.26346017","relation":{},"subject":[],"published":{"date-parts":[[2026,2,12]]},"subtype":"preprint"}}