Vis enkel innførsel

dc.contributor.authorKuttner, Samuel
dc.contributor.authorWickstrøm, Kristoffer Knutsen
dc.contributor.authorLubberink, Mark
dc.contributor.authorTolf, Andreas
dc.contributor.authorBurman, Joachim
dc.contributor.authorSundset, Rune
dc.contributor.authorJenssen, Robert
dc.contributor.authorAppel, Lieuwe
dc.contributor.authorAxelsson, Jan
dc.date.accessioned2021-06-19T17:44:43Z
dc.date.available2021-06-19T17:44:43Z
dc.date.issued2021-02-08
dc.description.abstract<p>Cerebral blood flow (CBF) can be measured with dynamic positron emission tomography (PET) of <sup>15</sup>O-labeled water by using tracer kinetic modelling. However, for quantification of regional CBF, an arterial input function (AIF), obtained from arterial blood sampling, is required. In this work we evaluated a novel, non-invasive approach for input function prediction based on machine learning (MLIF), against AIF for CBF PET measurements in human subjects. <p>Twenty-five subjects underwent two 10 min dynamic <sup>15</sup>O-water brain PET scans with continuous arterial blood sampling, before (baseline) and following acetazolamide medication. Three different image-derived time-activity curves were automatically segmented from the carotid arteries and used as input into a Gaussian process-based AIF prediction model, considering both baseline and acetazolamide scans as training data. The MLIF approach was evaluated by comparing AIF and MLIF curves, as well as whole-brain grey matter CBF values estimated by kinetic modelling derived with either AIF or MLIF. <p>The results showed that AIF and MLIF curves were similar and that corresponding CBF values were highly correlated and successfully differentiated before and after acetazolamide medication. In conclusion, our non-invasive MLIF method shows potential to replace the AIF obtained from blood sampling for CBF measurements using <sup>15</sup>O-water PET and kinetic modelling.en_US
dc.identifier.citationKuttner, Wickstrøm, Lubberink, Tolf, Burman, Sundset, Jenssen, Appel, Axelsson. Cerebral blood flow measurements with <sup>15</sup>O-water PET using a non-invasive machine-learning-derived arterial input function. Journal of Cerebral Blood Flow and Metabolism. 2021:1-13en_US
dc.identifier.cristinIDFRIDAID 1914467
dc.identifier.doi10.1177/0271678X21991393
dc.identifier.issn0271-678X
dc.identifier.issn1559-7016
dc.identifier.urihttps://hdl.handle.net/10037/21469
dc.language.isoengen_US
dc.publisherSageen_US
dc.relation.ispartofKuttner, S. (2021). Advancing Quantitative PET Imaging with Machine Learning. (Doctoral thesis). <a href=https://hdl.handle.net/10037/21186>https://hdl.handle.net/10037/21186</a>.
dc.relation.journalJournal of Cerebral Blood Flow and Metabolism
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.subjectVDP::Technology: 500::Medical technology: 620en_US
dc.subjectVDP::Teknologi: 500::Medisinsk teknologi: 620en_US
dc.titleCerebral blood flow measurements with 15O-water PET using a non-invasive machine-learning-derived arterial input functionen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel