2024
POUR-Net: A Population-Prior-Aided Over-Under-Representation Network for Low-Count PET Attenuation Map Generation
Zhou B, Hou J, Chen T, Zhou Y, Chen X, Xie H, Liu Q, Guo X, Xia M, Tsai Y, Panin V, Toyonaga T, Duncan J, Liu C. POUR-Net: A Population-Prior-Aided Over-Under-Representation Network for Low-Count PET Attenuation Map Generation. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10658051.Peer-Reviewed Original ResearchPET attenuation correctionLow-dose PETAttenuation correctionU-mapAttenuation mapElevated radiation doseRadiation doseEfficient feature extractionRadiation exposurePET imagingFinely detailed featuresBaseline methodsMitigate radiation exposureFeature extractionCorrectionMap generationGeneration machinesHigh-resolution brain phantom data, with flexible contrast: Validation on the NeuroExplorer (NX)
Gravel P, Toyonaga T, Gallezot J, Fontaine K, Martins S, Mulnix T, Carson R. High-resolution brain phantom data, with flexible contrast: Validation on the NeuroExplorer (NX). 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10656366.Peer-Reviewed Original ResearchQuantitative accuracyPhantom dataSpatial resolutionIterative reconstruction algorithmListmode dataAttenuation correctionPhantom studyPhantomResolution measurementsAttenuation propertiesReconstructed imagesReconstruction algorithmPET imagingCorrection accuracyResolutionScatteringAxial directionAttenuationContrastCorrectionAn Investigation on Cross-Tracer Generalizability of Deep Learning-based PET Attenuation Correction
Hou J, Chen T, Zhou Y, Chen X, Xie H, Liu Q, Xia M, Panin V, Liu C, Zhou B, Toyonaga T. An Investigation on Cross-Tracer Generalizability of Deep Learning-based PET Attenuation Correction. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10657095.Peer-Reviewed Original ResearchAttenuation correctionPET attenuation correctionQuantitative PET imagingAttenuation mapDL modelsDeep learning (DL)-based methodsTumor quantificationDL model trainingRadiation doseImmediate future workCompetitive performancePET imagingModel trainingPET signalCorrectionAnalysis of PETFuture workPreliminary resultsData availabilityRadiation
2022
Deep learning–based attenuation correction for whole-body PET — a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine
Toyonaga T, Shao D, Shi L, Zhang J, Revilla EM, Menard D, Ankrah J, Hirata K, Chen MK, Onofrey JA, Lu Y. Deep learning–based attenuation correction for whole-body PET — a multi-tracer study with 18F-FDG, 68 Ga-DOTATATE, and 18F-Fluciclovine. European Journal Of Nuclear Medicine And Molecular Imaging 2022, 49: 3086-3097. PMID: 35277742, PMCID: PMC10725742, DOI: 10.1007/s00259-022-05748-2.Peer-Reviewed Original ResearchConceptsNeural networkNovel deep learningNet neural networkPET/CT datasetsImage analysis metricsPhysics-based loss functionDeep learningCT-derived attenuation mapAttenuation mapLoss functionAnalysis metricsDetail recoveryTumor volume estimationMLAACT datasetsOSEM algorithmNetworkAlgorithmAttenuation correctionCorrection framework
2019
A Novel Loss Function Incorporating Imaging Acquisition Physics for PET Attenuation Map Generation Using Deep Learning
Shi L, Onofrey J, Revilla E, Toyonaga T, Menard D, Ankrah J, Carson R, Liu C, Lu Y. A Novel Loss Function Incorporating Imaging Acquisition Physics for PET Attenuation Map Generation Using Deep Learning. Lecture Notes In Computer Science 2019, 11767: 723-731. DOI: 10.1007/978-3-030-32251-9_79.Peer-Reviewed Original ResearchAttenuation mapAttenuation correctionCT-based attenuation mapAnnihilation eventsPET attenuation correctionLine integral projectionsPET raw dataInaccurate attenuation correctionCT attenuation mapsPhysicsMaximum likelihood reconstructionAC errorsMotion resultsLikelihood reconstructionLoss functionLarge biasΜ-CT