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
2019
Atlas-Based Multiorgan Segmentation for Dynamic Abdominal PET
Ren S, Laub P, Lu Y, Naganawa M, Carson R. Atlas-Based Multiorgan Segmentation for Dynamic Abdominal PET. IEEE Transactions On Radiation And Plasma Medical Sciences 2019, 4: 50-62. DOI: 10.1109/trpms.2019.2926889.Peer-Reviewed Original ResearchMultiorgan segmentationSegmentation methodDynamic image seriesDynamic imagesFrames of dataHyperparameter optimizationAutomatic frameworkSegmentation frameworkDynamic PET imagesSegmentation resultsGraph cutsFinal segmentationHyperparameter combinationsTemporal informationAtlas informationPET imagesTissue time-activity curvesManual segmentationSegmentationImage seriesGaussian distributionPrincipal component analysisBetter performanceImagesDifferent activity distributions
2007
Temporal and spatial blood information estimation using Bayesian ICA in dynamic cerebral positron emission tomography
Naganawa M, Kimura Y, Ishii K, Oda K, Ishiwata K. Temporal and spatial blood information estimation using Bayesian ICA in dynamic cerebral positron emission tomography. Digital Signal Processing 2007, 17: 979-993. DOI: 10.1016/j.dsp.2007.03.002.Peer-Reviewed Reviews, Practice Guidelines, Standards, and Consensus StatementsVolume imagesHuman brain PET studiesEnsemble learningSource imagesInformation estimationStandard independent component analysisBlood informationIndependent component analysisBlood volume imagesNonnegative constraintsCost functionImagesBrain PET studiesPET imagesGaussian distributionComponent analysisLearningTomographic imagesSchemePriorsCerebral positron emission tomographyInformationConstraintsMethod
2005
Extraction of a plasma time-activity curve from dynamic brain PET images based on independent component analysis
Naganawa M, Kimura Y, Ishii K, Oda K, Ishiwata K, Matani A. Extraction of a plasma time-activity curve from dynamic brain PET images based on independent component analysis. IEEE Transactions On Biomedical Engineering 2005, 52: 201-210. PMID: 15709657, DOI: 10.1109/tbme.2004.840193.Peer-Reviewed Original ResearchConceptsBrain PET imagesIndependent component analysisVolume imagesDynamic PET imagesPET imagesDynamic positron emission tomography (PET) dataAppropriate preprocessingBlood volume imagesImagesComponent analysisObjective functionPositron emission tomography dataComputer simulationsBrain FDG-PET studiesTomography dataPlasma time-activity curvePreprocessingNew methodEmission tomography dataSerial arterial blood samplingModelInput functionExtraction