{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T03:53:59Z","timestamp":1792122839032,"version":"4.4.0"},"reference-count":36,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":["Clin Nucl Med"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Multiplexed PET imaging revolutionized clinical decision-making by simultaneously capturing various radiotracer data in a single scan, enhancing diagnostic accuracy and patient comfort. Through a transformer-based deep learning, this study underscores the potential of advanced imaging techniques to streamline diagnosis and improve patient outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and Methods<\/jats:title>\n                    <jats:p>\n                      The research cohort consisted of 120 patients spanning from cognitively unimpaired individuals to those with mild cognitive impairment, dementia, and other mental disorders. Patients underwent various imaging assessments, including 3D T1-weighted MRI, amyloid PET scans using either\n                      <jats:sup>18<\/jats:sup>\n                      F-florbetapir (FBP) or\n                      <jats:sup>18<\/jats:sup>\n                      F-flutemetamol (FMM), and\n                      <jats:sup>18<\/jats:sup>\n                      F-FDG PET. Summed images of FMM\/FBP and FDG were used as proxy for simultaneous scanning of 2 different tracers. A SwinUNETR model, a convolution-free transformer architecture, was trained for image translation. The model was trained using mean square error loss function and 5-fold cross-validation. Visual evaluation involved assessing image similarity and amyloid status, comparing synthesized images with actual ones. Statistical analysis was conducted to determine the significance of differences.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Visual inspection of synthesized images revealed remarkable similarity to reference images across various clinical statuses. The mean centiloid bias for dementia, mild cognitive impairment, and healthy control subjects and for FBP tracers is 15.70 \u00b1 29.78, 0.35 \u00b1 33.68, and 6.52 \u00b1 25.19, respectively, whereas for FMM, it is \u22126.85 \u00b1 25.02, 4.23 \u00b1 23.78, and 5.71 \u00b1 21.72, respectively. Clinical evaluation by 2 readers further confirmed the model's efficiency, with 97 FBP\/FMM and 63 FDG synthesized images (from 120 subjects) found similar to ground truth diagnoses (rank 3), whereas 3 FBP\/FMM and 15 FDG synthesized images were considered nonsimilar (rank 1). Promising sensitivity, specificity, and accuracy were achieved in amyloid status assessment based on synthesized images, with an average sensitivity of 95 \u00b1 2.5, specificity of 72.5 \u00b1 12.5, and accuracy of 87.5 \u00b1 2.5. Error distribution analyses provided valuable insights into error levels across brain regions, with most falling between \u22120.1 and +0.2 SUV ratio. Correlation analyses demonstrated strong associations between actual and synthesized images, particularly for FMM images (FBP: Y = 0.72X + 20.95,\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.54; FMM: Y = 0.65X + 22.77,\n                      <jats:italic toggle=\"yes\">R<\/jats:italic>\n                      <jats:sup>2<\/jats:sup>\n                      = 0.77).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrated the potential of a novel convolution-free transformer architecture, SwinUNETR, for synthesizing realistic FDG and FBP\/FMM images from summation scans mimicking simultaneous dual-tracer imaging.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/rlu.0000000000005511","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T01:28:21Z","timestamp":1730165301000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":8,"title":["Tracer-Separator"],"prefix":"10.1097","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-2060","authenticated-orcid":false,"given":"Amirhossein","family":"Sanaat","sequence":"first","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyi","family":"Hu","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cecilia","family":"Boccalini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1233-9576","authenticated-orcid":false,"given":"Yazdan","family":"Salimi","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2087-9721","authenticated-orcid":false,"given":"Zahra","family":"Mansouri","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eliluane Pirazzo Andrade","family":"Teixeira","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Mathoux","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-698X","authenticated-orcid":false,"given":"Valentina","family":"Garibotto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7559-5297","authenticated-orcid":false,"given":"Habib","family":"Zaidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"bib1-20241203","first-page":"924824","article-title":"18F-FDG \/18F-choline dual-tracer PET behavior and tumor differentiation in hepatocellular carcinoma. A systematic review","volume":"9","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"bib2-20241203","doi-asserted-by":"crossref","first-page":"85","DOI":"10.2967\/jnmt.118.215582","article-title":"Small cell transformation of metastatic prostate adenocarcinoma diagnosed by dual-tracer PET\/CT ((68)Ga-PSMA and (18)F-FDG): potential clinical utility in therapeutic decision making and treatment monitoring","volume":"47","year":"2019","journal-title":"J Nucl Med Technol"},{"key":"bib3-20241203","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1186\/s13550-023-01024-y","article-title":"A dual-tracer approach using [(11)C]CH and [(18)F]FDG in HCC clinical decision making","volume":"13","year":"2023","journal-title":"EJNMMI Res"},{"key":"bib4-20241203","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1001\/jamaneurol.2023.0997","article-title":"Clinical effect of early vs late amyloid positron emission tomography in memory clinic patients: the AMYPAD-DPMS randomized clinical trial","volume":"80","year":"2023","journal-title":"JAMA Neurol"},{"key":"bib5-20241203","doi-asserted-by":"crossref","first-page":"6122","DOI":"10.1038\/s41467-023-41897-0","article-title":"PET-measured human dopamine synthesis capacity and receptor availability predict trading rewards and time-costs during foraging","volume":"14","year":"2023","journal-title":"Nat Commun"},{"key":"bib6-20241203","doi-asserted-by":"crossref","first-page":"085016","DOI":"10.1088\/1361-6560\/acc723","article-title":"Design of a generic method for single dual-tracer PET imaging acquisition in clinical routine","volume":"68","year":"2023","journal-title":"Phys Med Biol"},{"key":"bib7-20241203","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1038\/jcbfm.2009.53","article-title":"Signal separation and parameter estimation in noninvasive dual-tracer PET scans using reference-region approaches","volume":"29","year":"2009","journal-title":"J Cereb Blood Flow Metab"},{"key":"bib8-20241203","first-page":"4897","article-title":"Design and utilisation of protocols to characterise dynamic PET uptake of two tracers using basis pursuit","volume":"62","year":"2017","journal-title":"Mol Imaging Biol"},{"key":"bib9-20241203","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TNS.2005.858230","article-title":"Feasibility of rapid multitracer PET tumor imaging","volume":"52","year":"2005","journal-title":"IEEE Trans Nucl Sci"},{"key":"bib10-20241203","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1007\/s11307-013-0631-1","article-title":"Dual-tracer PET using generalized factor analysis of dynamic sequences","volume":"15","year":"2013","journal-title":"Mol Imaging Biol"},{"key":"bib11-20241203","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1038\/s41551-023-01060-y","article-title":"Simultaneous quantitative imaging of two PET radiotracers via the detection of positron-electron annihilation and prompt gamma emissions","volume":"7","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"bib12-20241203","doi-asserted-by":"crossref","first-page":"4089","DOI":"10.3390\/app13074089","article-title":"Dual-tracer PET image separation by deep learning: a simulation study","volume":"13","year":"2023","journal-title":"Appl Sci"},{"key":"bib13-20241203","doi-asserted-by":"crossref","first-page":"2588","DOI":"10.1109\/TNS.2017.2736644","article-title":"Separation of a mixture of simultaneous dual-tracer PET signals: a data-driven approach","volume":"64","year":"2017","journal-title":"IEEE Trans Nucl Sci"},{"key":"bib14-20241203","doi-asserted-by":"crossref","first-page":"185016","DOI":"10.1088\/1361-6560\/ab3103","article-title":"Three-dimensional convolutional neural networks for simultaneous dual-tracer PET imaging","volume":"64","year":"2019","journal-title":"Phys Med Biol"},{"key":"bib15-20241203","doi-asserted-by":"crossref","first-page":"165681","DOI":"10.1016\/j.nima.2021.165681","article-title":"Separation of dual-tracer PET signals using a deep stacking network","volume":"1013","year":"2021","journal-title":"Nucl Instr Meth A"},{"key":"bib17-20241203","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1109\/TRPMS.2019.2897120","article-title":"Deep-learning-based separation of a mixture of dual-tracer single-acquisition PET signals with equal half-lives: a simulation study","volume":"3","year":"2019","journal-title":"IEEE Trans Rad Plasma Med Sci"},{"key":"bib18-20241203","doi-asserted-by":"crossref","first-page":"4585","DOI":"10.1002\/mp.15566","article-title":"Temporal information-guided dynamic dual-tracer PET signal separation network","volume":"49","year":"2022","journal-title":"Med Phys"},{"key":"bib19-20241203","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s13550-023-00955-w","article-title":"Direct reconstruction for simultaneous dual-tracer PET imaging based on multi-task learning","volume":"13","year":"2023","journal-title":"EJNMMI Res"},{"key":"bib20-20241203","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1146\/annurev-bioeng-082420-020343","article-title":"Quantitative molecular positron emission tomography imaging using advanced deep learning techniques","volume":"23","year":"2021","journal-title":"Annu Rev Biomed Eng"},{"key":"bib21-20241203","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.ejmp.2021.03.008","article-title":"The promise of artificial intelligence and deep learning in PET and SPECT imaging","volume":"83","year":"2021","journal-title":"Phys Med"},{"key":"bib22-20241203","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.2967\/jnumed.121.263239","article-title":"Nuclear medicine and artificial intelligence: best practices for evaluation (the RELAINCE guidelines)","volume":"63","year":"2022","journal-title":"J Nucl Med"},{"key":"bib23-20241203","doi-asserted-by":"crossref","first-page":"4","DOI":"10.2967\/jnumed.122.265000","article-title":"Artificial intelligence for PET and SPECT image enhancement","volume":"65","year":"2024","journal-title":"J Nucl Med"},{"key":"bib24-20241203","first-page":"816","article-title":"An investigation of a double-tracer technique for positron computerized tomography","volume":"23","year":"1982","journal-title":"J Nucl Med"},{"key":"bib25-20241203","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1007\/s11307-010-0370-5","article-title":"Simultaneous dual-tracer PET imaging of the rat brain and its application in the study of cerebral ischemia","volume":"13","year":"2011","journal-title":"Mol Imaging Biol"},{"key":"bib26-20241203","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1088\/0031-9155\/35\/2\/005","article-title":"Feasibility of simultaneous and sequentially administered dual tracer protocols for measurement of regional cerebral haematocrit using positron emission tomography","volume":"35","year":"1990","journal-title":"Phys Med Biol"},{"key":"bib27-20241203","first-page":"2611","article-title":"Noise properties of simultaneous dual tracer PET imaging","volume":"2005","year":"2005","journal-title":"IEEE Nucl Sci Symp Conference Rec"},{"key":"bib28-20241203","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1097\/00004647-200112000-00013","article-title":"Dual-[11C]tracer single-acquisition positron emission tomography studies","volume":"21","year":"2001","journal-title":"J Cereb Blood Flow Metab"},{"key":"bib29-20241203","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1109\/TMI.2021.3112783","article-title":"Machine learning\u2013based noninvasive quantification of single-imaging session dual-tracer (18)F-FDG and (68)Ga-DOTATATE dynamic PET-CT in oncology","volume":"41","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"bib30-20241203","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1007\/s00259-021-05603-w","article-title":"EANM procedure guidelines for brain PET imaging using [(18)F]FDG, version 3","volume":"49","year":"2022","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"bib31-20241203","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s00259-019-04536-9","article-title":"The a\/T\/N model applied through imaging biomarkers in a memory clinic","volume":"47","year":"2020","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"bib32-20241203","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jalz.2014.07.003","article-title":"The centiloid project: standardizing quantitative amyloid plaque estimation by PET","volume":"11","year":"2015","journal-title":"Alzheimers Dement"},{"key":"bib33-20241203","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","year":"2021","journal-title":"arXiv preprint arXiv:210505537"},{"key":"bib34-20241203","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vision"},{"key":"bib35-20241203","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","year":"2020","journal-title":"arXiv preprint arXiv:201011929"},{"key":"bib36-20241203","first-page":"429","article-title":"Single-scan dual-tracer FLT + FDG PET tumor characterization","volume":"58","year":"2013","journal-title":"Mol Imaging Biol"},{"key":"bib37-20241203","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.1007\/s00259-024-06618-9","article-title":"Deep transformer-based personalized dosimetry from SPECT\/CT images: a hybrid approach for [177Lu]Lu-DOTATATE radiopharmaceutical therapy","volume":"51","year":"2024","journal-title":"Eur J Nucl Med Mol Imaging"}],"container-title":["Clinical Nuclear Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T18:01:13Z","timestamp":1733248873000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/RLU.0000000000005511"}},"subtitle":["A Deep Learning Model for Brain PET Dual-Tracer (18F-FDG and Amyloid) Separation"],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/rlu.0000000000005511","relation":{},"ISSN":["1536-0229","0363-9762"],"issn-type":[{"value":"1536-0229","type":"electronic"},{"value":"0363-9762","type":"print"}],"subject":[],"published":{"date-parts":[[2024,10,29]]}}}