2023
Unsupervised Deep Learning with Self-Validation in Dynamic PET Dose Reduction
Li A, Syed M, Naganawa M, Matuskery D, Carson R, Tang J. Unsupervised Deep Learning with Self-Validation in Dynamic PET Dose Reduction. 2023, 00: 1-1. DOI: 10.1109/nssmicrtsd49126.2023.10337886.Peer-Reviewed Original ResearchNoise reductionSingle-frame methodsImage featuresImage framesTraining dataUnsupervised methodSpatiotemporal informationKinetic modelingDeep imageDynamic PETHard thresholdComposite imageBetter performanceImagesRobust performanceHigh noiseImaging dataFrame methodVast numberKinetic modeling analysisNoise levelFrameSelf-ValidationDynamic PET imagingCapability
2020
Data-Driven Motion Detection and Event-by-Event Correction for Brain PET: Comparison with Vicra
Lu Y, Naganawa M, Toyonaga T, Gallezot JD, Fontaine K, Ren S, Revilla EM, Mulnix T, Carson RE. Data-Driven Motion Detection and Event-by-Event Correction for Brain PET: Comparison with Vicra. Journal Of Nuclear Medicine 2020, 61: 1397-1403. PMID: 32005770, PMCID: PMC7456171, DOI: 10.2967/jnumed.119.235515.Peer-Reviewed Original ResearchConceptsData-driven algorithmMotion correction methodMotion tracking informationHead motionCentroid of distributionMotion-compensated reconstructionLarge head motionsMotion correction frameworkUser-defined thresholdPET raw dataDynamic datasetsTracking informationImage registrationMotion detectionRaw dataSuch time pointsImage qualityBetter performanceMotion correctionAlgorithmLine of responseCorrection frameworkBrain PET studiesCentral coordinatesTracer kinetic modeling