{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T20:45:32Z","timestamp":1793047532935,"version":"4.5.0"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T00:00:00Z","timestamp":1712793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100016934","name":"Troms\u00f8 Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016934","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Nucl. Med."],"abstract":"<jats:p>Dynamic positron emission tomography and kinetic modeling play a critical role in tracer development research using small animals. Kinetic modeling from dynamic PET imaging requires accurate knowledge of an input function, ideally determined through arterial blood sampling. Arterial cannulation in mice, however, requires complex, time-consuming and terminal surgery, meaning that longitudinal studies are impossible. The aim of the current work was to develop and evaluate a non-invasive, deep-learning-based prediction model (DLIF) that directly takes the PET data as input to predict a usable input function. We first trained and evaluated the DLIF model on 68 [<jats:sup>18<\/jats:sup>F]Fluorodeoxyglucose mouse scans with image-derived targets using cross validation. Subsequently, we evaluated the performance of a trained DLIF model on an external dataset consisting of 8 mouse scans where the input function was measured by continuous arterial blood sampling. The results showed that the predicted DLIF and image-derived targets were similar, and the net influx rate constants following from Patlak modeling using DLIF as input function were strongly correlated to the corresponding values obtained using the image-derived input function. There were somewhat larger discrepancies when evaluating the model on the external dataset, which could be attributed to systematic differences in the experimental setup between the two datasets. In conclusion, our non-invasive DLIF prediction method may be a viable alternative to arterial blood sampling in small animal [<jats:sup>18<\/jats:sup>F]FDG imaging. With further validation, DLIF could overcome the need for arterial cannulation and allow fully quantitative and longitudinal experiments in PET imaging studies of mice.<\/jats:p>","DOI":"10.3389\/fnume.2024.1372379","type":"journal-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T04:53:52Z","timestamp":1712811232000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep-learning-derived input function in dynamic [18F]FDG PET imaging of mice"],"prefix":"10.3389","volume":"4","author":[{"given":"Samuel","family":"Kuttner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi T.","family":"Luppino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurence","family":"Convert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Otman","family":"Sarrhini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Lecomte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael C.","family":"Kampffmeyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rune","family":"Sundset","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Jenssen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,4,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"S102","DOI":"10.1102\/1470-7330.2006.9098","article-title":"Pet tracer development\u2014a tale of mice, men","volume":"6","author":"Hicks","year":"2006","journal-title":"Cancer Imaging"},{"key":"B2","doi-asserted-by":"publisher","first-page":"157","DOI":"10.2967\/jnmt.111.098632","article-title":"Small-animal pet: what is it,, why do we need it?","volume":"40","author":"Yao","year":"2012","journal-title":"J Nucl Med Technol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s40291-013-0062-3","article-title":"Preclinical imaging: an essential ally in modern biosciences","volume":"18","author":"Cunha","year":"2014","journal-title":"Mol Diagn Ther"},{"key":"B4","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1097\/00004647-200106000-00002","article-title":"Positron emission tomography compartmental models","volume":"21","author":"Gunn","year":"2001","journal-title":"J Cereb Blood Flow Metab"},{"key":"B5","first-page":"1","article-title":"Graphical evaluation of blood-to-brain transfer constants from multiple-time uptake data","volume-title":"J Cereb Blood Flow Metab","author":"Patlak","year":"1983"},{"key":"B6","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1038\/jcbfm.1985.87","article-title":"Graphical evaluation of blood-to-brain transfer constants from multiple-time uptake data. generalizations","volume":"5","author":"Patlak","year":"1985","journal-title":"J Cereb Blood Flow Metab"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1002\/mp.13366","article-title":"Comparative assessment of linear least-squares, nonlinear least-squares,, Patlak graphical method for regional and local quantitative tracer kinetic modeling in cerebral dynamic 18F-FDG pet","volume":"46","author":"Bouall\u00e8gue","year":"2019","journal-title":"Med Phys"},{"key":"B8","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1109\/TRPMS.2020.3025086","article-title":"Pet parametric imaging: past, present, and future","volume":"4","author":"Wang","year":"2020","journal-title":"IEEE Trans Radiat Plasma Med Sci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"132","DOI":"10.2967\/jnumed.112.107474","article-title":"Quantification of brain glucose metabolism by 18F-FDG pet with real-time arterial and image-derived input function in mice","volume":"54","author":"Alf","year":"2013","journal-title":"J Nucl Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1016\/j.nucmedbio.2005.06.012","article-title":"Measurement of input functions in rodents: challenges and solutions","volume":"32","author":"Laforest","year":"2005","journal-title":"Nucl Med Biol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1007\/s00259-006-0121-7","article-title":"Simplified quantification of small animal [18F]FDG pet studies using a standard arterial input function","volume":"33","author":"Meyer","year":"2006","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B12","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1007\/s11307-016-0954-9","article-title":"Novel approach to repeated arterial blood sampling in small animal pet: application in a test-retest study with the adenosine a1 receptor ligand [11C]MPDX","volume":"18","author":"Sijbesma","year":"2016","journal-title":"Mol Imaging Biol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/s11307-020-01556-y","article-title":"Feasibility of longitudinal brain pet with real-time arterial input function in rats","volume":"23","author":"Rey-Bretal","year":"2021","journal-title":"Mol Imaging Biol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"035022","DOI":"10.1088\/2057-1976\/AC4C29","article-title":"The ultra high sensitivity blood counter: a compact, MRI-compatible, radioactivity counter for pharmacokinetic studies in \u03bcl volumes","volume":"8","author":"Convert","year":"2022","journal-title":"Biomed Phys Eng Express"},{"key":"B15","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1148\/radiology.188.1.8511286","article-title":"Noninvasive quantitative fluorodeoxyglucose PET studies with an estimated input function derived from a population-based arterial blood curve","volume":"188","author":"Takikawa","year":"1993","journal-title":"Radiology"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.2967\/jnumed.113.127381","article-title":"Image-derived input function from the vena cava for 18F-FDG PET studies in rats and mice","volume":"55","author":"Lanz","year":"2014","journal-title":"J Nucl Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1007\/s11307-018-1300-1","article-title":"Quantification of positron emission tomography data using simultaneous estimation of the input function: validation with venous blood and replication of clinical studies","volume":"21","author":"Bartlett","year":"2019","journal-title":"Mol Imaging Biol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2018.2890459","article-title":"Quantifying brain [18F]FDG uptake noninvasively by combining medical health records and dynamic PET imaging data","volume":"2194","author":"Roccia","year":"2019","journal-title":"IEEE J Biomed Heal. Inform"},{"key":"B19","first-page":"1715","article-title":"Correction of partial-volume effect for pet striatal imaging: fast implementation and study of robustness","volume":"43","author":"Frouin","year":"2002","journal-title":"J Nucl Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1038\/jcbfm.2013.29","article-title":"Partial volume correction using structural-functional synergistic resolution recovery: comparison with geometric transfer matrix method","volume":"33","author":"Kim","year":"2013","journal-title":"J Cereb Blood Flow Metab"},{"key":"B21","doi-asserted-by":"publisher","first-page":"606","DOI":"10.2967\/jnumed.107.047613","article-title":"Spillover, partial-volume correction for image-derived input functions for small-animal 18F-FDG pet studies","volume":"49","author":"Fang","year":"2008","journal-title":"J Nucl Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/4233.681168","article-title":"A technique for extracting physiological parameters, the required input function simultaneously from PET image measurements: theory and simulation study","volume":"1","author":"Feng","year":"1997","journal-title":"IEEE Trans Inf Technol Biomed"},{"key":"B23","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4233.908397","article-title":"Simultaneous estimation of physiological parameters and the input function\u2014in vivo PET data","volume":"5","author":"Wong","year":"2001","journal-title":"IEEE Trans Inf Technol Biomed"},{"key":"B24","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Annu Rev Biomed Eng"},{"key":"B25","doi-asserted-by":"publisher","first-page":"015020","DOI":"10.1088\/2057-1976\/ab6496","article-title":"Machine learning derived input-function in a dynamic 18 F-FDG PET study of mice","volume":"6","author":"Kuttner","year":"2020","journal-title":"Biomed Phys Eng Express"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2229","DOI":"10.1177\/0271678X21991393","article-title":"Cerebral blood flow measurements with 15 o-water pet using a non-invasive machine-learning-derived arterial input function","volume":"41","author":"Kuttner","year":"2021","journal-title":"J Cereb Blood Flow Metab"},{"key":"B27","first-page":"1394","article-title":"Direct estimation of input function based on fine-tuned deep learning method in dynamic PET imaging","volume":"61","author":"Wang","year":"2020","journal-title":"J Nucl Med"},{"key":"B28","first-page":"1","article-title":"Blood input function estimation in positron emission tomography with deep learning","author":"Varny\u00fa","year":"2021"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/20587384211033683","article-title":"Positron emission tomography and single photon emission computed tomography imaging of tertiary lymphoid structures during the development of lupus nephritis","volume":"35","author":"Dorraji","year":"2021","journal-title":"Int J Immunopathol Pharmacol"},{"key":"B30","first-page":"1836","article-title":"SUV: standard uptake or silly useless value?","volume":"36","author":"Keyes","year":"1995","journal-title":"J Nucl Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1002\/jat.727","article-title":"A good practice guide to the administration of substances and removal of blood, including routes and volumes","volume":"21","author":"Diehl","year":"2001","journal-title":"J Appl Toxicol"},{"key":"B32","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"B33","author":"Ioffe","year":""},{"key":"B34","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"Maas","year":"2013"},{"key":"B35","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B36","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","article-title":"Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation","volume":"48","author":"Wong","year":"2015","journal-title":"Pattern Recognit"},{"key":"B38","article-title":"On the convergence of ADAM and beyond","author":"Reddi","year":"2018"},{"key":"B39","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1080\/0020739X.2011.573876","article-title":"Orthogonal regression: a teaching perspective","volume":"43","author":"Carr","year":"2012","journal-title":"Int J Math Educ Sci Technol"},{"key":"B40","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/2191-219X-2-26","article-title":"Impact of inherent variability and experimental parameters on the reliability of small animal pet data","volume":"2","author":"Martic-Kehl","year":"2012","journal-title":"EJNMMI Res"},{"key":"B41","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13098-023-01038-5","article-title":"Dynamic evolution and mechanism of myocardial glucose metabolism in different functional phenotypes of diabetic cardiomyopathy\u2014a study based on 18F-FDG micropet myocardial metabolic imaging","volume":"15","author":"Shao","year":"2023","journal-title":"Diabetol Metab Syndr"},{"key":"B42","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J Big Data"},{"key":"B43","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1111\/j.1471-6712.2012.01052.x","article-title":"The large sample size fallacy","volume":"27","author":"Lantz","year":"2013","journal-title":"Scand J Caring Sci"},{"key":"B44","first-page":"999","article-title":"Impact of animal handling on the results of 18F-FDG pet studies in mice","volume":"47","author":"Fueger","year":"2006","journal-title":"J Nucl Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"800","DOI":"10.2967\/jnumed.110.085092","article-title":"Effects of administration route, dietary condition, and blood glucose level on kinetics and uptake of 18F-FDG in mice","volume":"52","author":"Wong","year":"2011","journal-title":"J Nucl Med"},{"key":"B46","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/2191-219X-1-8","article-title":"Influence of dietary state and insulin on myocardial, skeletal muscle and brain [f]-fluorodeoxyglucose kinetics in mice","volume":"1","author":"Kreissl","year":"2011","journal-title":"EJNMMI Res"},{"key":"B47","doi-asserted-by":"publisher","first-page":"21","DOI":"10.4236\/ami.2012.23004","article-title":"Inhibition of physiologic myocardial FDG uptake in normal rodents: comparison of four pre-scan preparation protocols","volume":"2","author":"Langah","year":"2012","journal-title":"Adv J Mol Imaging"},{"key":"B48","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3390\/diagnostics2040042","article-title":"Importance of attenuation correction (AC) for small animal pet imaging","volume":"2","author":"Ali","year":"2012","journal-title":"Diagnostics"},{"key":"B49","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2967\/jnumed.106.038182","article-title":"In vivo quantitation of glucose metabolism in mice using small-animal PET and a microfluidic device","volume":"48","author":"Wu","year":"2007","journal-title":"J Nucl Med"}],"container-title":["Frontiers in Nuclear Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnume.2024.1372379\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T08:45:28Z","timestamp":1728290728000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnume.2024.1372379\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,11]]},"references-count":49,"alternative-id":["10.3389\/fnume.2024.1372379"],"URL":"https:\/\/doi.org\/10.3389\/fnume.2024.1372379","relation":{},"ISSN":["2673-8880"],"issn-type":[{"value":"2673-8880","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,11]]},"article-number":"1372379"}}