{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T03:26:04Z","timestamp":1772249164928,"version":"3.50.1"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>\n                      Neuroinflammation, a pathophysiological process involved in numerous disorders, is typically imaged using [\n                      <jats:sup>11<\/jats:sup>\n                      C]PBR28 (or TSPO) PET. However, this technique is limited by high costs and ionizing radiation, restricting its widespread clinical use. MRI, a more accessible alternative, is commonly used for structural or functional imaging, but when used using traditional approaches has limited sensitivity to specific molecular processes. This study aims to develop a deep learning model to generate TSPO PET images from structural MRI data collected in human subjects.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 204 scans, from participants with knee osteoarthritis (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f15 scanned once, 15 scanned twice, 14 scanned three times), back pain (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f40 scanned twice, 3 scanned three times), and healthy controls (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f28, scanned once), underwent simultaneous 3\u202fT MRI and [\n                      <jats:sup>11<\/jats:sup>\n                      C]PBR28 TSPO PET scans. A 3D U-Net model was trained on 80% of these PET-MRI pairs and validated using 5-fold cross-validation. The model\u2019s accuracy in reconstructed PET from MRI only was assessed using various intensity and noise metrics.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved a low voxel-wise mean squared error (0.0033\u202f\u00b1\u202f0.0010) across all folds and a median contrast-to-noise ratio of 0.0640\u202f\u00b1\u202f0.2500 when comparing true to reconstructed PET images. The synthesized PET images accurately replicated the spatial patterns observed in the original PET data. Additionally, the reconstruction accuracy was maintained even after spatial normalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This study demonstrates that deep learning can accurately synthesize TSPO PET images from conventional, T1-weighted MRI. This approach could enable low-cost, noninvasive neuroinflammation imaging, expanding the clinical applicability of this imaging method.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fninf.2025.1633273","type":"journal-article","created":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T04:14:53Z","timestamp":1757304893000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generation of synthetic TSPO PET maps from structural MRI images"],"prefix":"10.3389","volume":"19","author":[{"given":"Matteo","family":"Ferrante","sequence":"first","affiliation":[]},{"given":"Marianna","family":"Inglese","sequence":"additional","affiliation":[]},{"given":"Ludovica","family":"Brusaferri","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Toschi","sequence":"additional","affiliation":[]},{"given":"Marco L.","family":"Loggia","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.bbi.2018.09.018","article-title":"Brain glial activation in fibromyalgia - a multi-site positron emission tomography investigation","volume":"75","author":"Albrecht","year":"2019","journal-title":"Brain Behav. Immun."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1021\/acschemneuro.6b00056","article-title":"In vivo imaging of human Neuroinflammation","volume":"7","author":"Albrecht","year":"2016","journal-title":"ACS Chem. Neurosci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1093\/brain\/awab336","article-title":"Neuroimmune signatures in chronic low back pain subtypes","volume":"145","author":"Alshelh","year":"2022","journal-title":"Brain"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"4640","DOI":"10.3390\/s22124640","article-title":"FDG-PET to T1 weighted MRI translation with 3d elicit generative adversarial network (E-GAN)","volume":"22","author":"Bazangani","year":"2022","journal-title":"Sensors"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"3805","DOI":"10.1073\/pnas.74.9.3805","article-title":"Specific benzodiazepine receptors in rat brain characterized by high-affinity (3H)diazepam binding","volume":"74","author":"Braestrup","year":"1977","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref6","author":"Cardoso","year":"2022"},{"key":"ref7","author":"Chollet","year":"2017"},{"key":"ref8","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1016\/j.neuroimage.2006.01.021","article-title":"An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest","volume":"31","author":"Desikan","year":"2006","journal-title":"Neuroimage"},{"key":"ref10","author":"Emami","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.3390\/biom12101453","article-title":"Targeting Neuroinflammation in osteoarthritis with intra-articular Adelmidrol","volume":"12","author":"Guida","year":"2022","journal-title":"Biomolecules"},{"key":"ref12","author":"Hu","year":"2020"},{"key":"ref13","first-page":"1","article-title":"Cross-modality synthesis from MRI to PET using adversarial U-net with different normalization","author":"Hu","year":"2019"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.632","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.2967\/jnumed.113.136341","article-title":"An SPM8-based approach for attenuation correction combining segmentation and non-rigid template formation: application to simultaneous PET\/MR brain imaging","volume":"55","author":"Izquierdo-Garcia","year":"2014","journal-title":"J. Nucl. Med."},{"key":"ref16","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":"ref17","volume-title":"Inferring PET from MRI with pix2pix: Benelux conference on artificial intelligence","author":"Jung","year":"2018"},{"key":"ref18","first-page":"1836","article-title":"SUV: Standard uptake or silly useless value?","volume":"4","author":"Keyes","year":"1995","journal-title":"J. Nucl. Med."},{"key":"ref19","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/978-3-319-10443-0_39","article-title":"Deep learning based imaging data completion for improved brain disease diagnosis","volume-title":"Medical image Computing and computer-assisted intervention \u2013 MICCAI 2014","author":"Li","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1093\/brain\/awu377","article-title":"Evidence for brain glial activation in chronic pain patients","volume":"138","author":"Loggia","year":"2015","journal-title":"Brain"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/s00259-020-05166-2","article-title":"Cellular sources of TSPO expression in healthy and diseased brain","volume":"49","author":"Nutma","year":"2021","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/jcbfm.2011.147","article-title":"An 18-kDa translocator protein (TSPO) polymorphism explains differences in binding affinity of the PET radioligand PBR28","volume":"32","author":"Owen","year":"2012","journal-title":"J. Cereb. Blood Flow Metab."},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-87240-3_46","article-title":"Collaborative image synthesis and disease diagnosis for classification of neurodegenerative disorders with incomplete multi-modal Neuroimages","author":"Pan","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/s40336-015-0142-y","article-title":"MRI\/MRS in neuroinflammation: methodology and applications","volume":"3","author":"Quarantelli","year":"2015","journal-title":"Clin. Translat. Imaging"},{"key":"ref25","author":"Shin","year":"2020"},{"key":"ref26","author":"Sikka","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"5326","DOI":"10.21037\/qims-22-116","article-title":"High-quality PET image synthesis from ultra-low-dose PET\/MRI using bi-task deep learning","volume":"12","author":"Sun","year":"2022","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.01071","article-title":"DUAL-GLOW: conditional flow-based generative model for modality transfer","author":"Sun","year":"2019"},{"key":"ref29","author":"Theodorou","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"119898","DOI":"10.1016\/j.neuroimage.2023.119898","article-title":"Applications of generative adversarial networks in neuroimaging and clinical neuroscience","volume":"269","author":"Wang","year":"2023","journal-title":"NeuroImage"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/1471-2377-6-12","article-title":"COX-2, CB2 and P2X7-immunoreactivities are increased in activated microglial cells\/macrophages of multiple sclerosis and amyotrophic lateral sclerosis spinal cord","volume":"6","author":"Yiangou","year":"2006","journal-title":"BMC Neurol."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.nucmedbio.2014.11.003","article-title":"Comparison of standardized uptake values with volume of distribution for quantitation of [(11)C]PBR28 brain uptake","volume":"42","author":"Yoder","year":"2015","journal-title":"Nucl. Med. Biol."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"106676","DOI":"10.1016\/j.cmpb.2022.106676","article-title":"BPGAN: brain PET synthesis from MRI using generative adversarial network for multi-modal Alzheimer\u2019s disease diagnosis","volume":"217","author":"Zhang","year":"2022","journal-title":"Comput. Methods Prog. Biomed."}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1633273\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T04:14:54Z","timestamp":1757304894000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1633273\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":33,"alternative-id":["10.3389\/fninf.2025.1633273"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2025.1633273","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.09.27.615379","asserted-by":"object"}]},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,8]]},"article-number":"1633273"}}