Jinsong Ouyang, PhD
Associate Professor of Radiology and Biomedical ImagingCards
About
Titles
Associate Professor of Radiology and Biomedical Imaging
Appointments
Radiology & Biomedical Imaging
Associate Professor on TermPrimary
Other Departments & Organizations
Education & Training
- PhD
- University of Colorado, Physics (1992)
Research
Publications
2025
Bayesian Posterior Distribution Estimation of Kinetic Parameters in Dynamic Brain PET Using Generative Deep Learning Models
Djebra Y, Liu X, Marin T, Tiss A, Dhaynaut M, Guehl N, Johnson K, Fakhri G, Ma C, Ouyang J. Bayesian Posterior Distribution Estimation of Kinetic Parameters in Dynamic Brain PET Using Generative Deep Learning Models. IEEE Transactions On Medical Imaging 2025, PP: 1-1. PMID: 40663684, PMCID: PMC12318411, DOI: 10.1109/tmi.2025.3588859.Peer-Reviewed Original ResearchPosterior distributions of kinetic parametersEfficiency of deep learningGenerative deep learning modelsConditional variational autoencoderDeep learning modelsComputational efficiencyMetropolis-Hastings MCMCPosterior distributionHyperphosphorylated tauDynamic brain positron emission tomographyWGAN-GPDual decodersWasserstein GANVariational autoencoderKinetic parametersDeep learningComputational needsBayesian inferenceP-tauLearning modelsAlzheimer's diseaseNeurodegenerative diseasesComputation timeMCMC methodsEstimation of kinetic parametersMixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation
Wei J, Zhao X, Woo J, Ouyang J, Fakhri G, Chen Q, Liu X. Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation. 2025, 00: 6450-6460. DOI: 10.1109/cvprw67362.2025.00642.Peer-Reviewed Original ResearchSingle domain generalizationEnd-to-endShape priorsGeneralization capabilityEnd-to-end mannerDictionary learning methodMedical image segmentationMixture-of-expertsMultiple public datasetsShape mapsDictionary atomsDictionary learningDictionary sizeShape dictionaryRepresentational powerDomain generalizationPublic datasetsGating networkImage segmentationMedical segmentationLearning methodsShape informationDictionaryBidirectional integrationOverfittingDual Prompting for Diverse Count-Level Pet Denoising
Liu X, Huang Y, Marin T, Vafay Eslahi S, Tiss A, Chemli Y, Johnson K, El Fakhri G, Ouyang J. Dual Prompting for Diverse Count-Level Pet Denoising. 2011 IEEE International Symposium On Biomedical Imaging: From Nano To Macro 2025, 00: 1-5. PMID: 40831530, PMCID: PMC12360122, DOI: 10.1109/isbi60581.2025.10980695.Peer-Reviewed Original ResearchPET Mapping of Receptor Occupancy Using Joint Direct Parametric Reconstruction
Marin T, Belov V, Chemli Y, Ouyang J, Najmaoui Y, Fakhri G, Duvvuri S, Iredale P, Guehl N, Normandin M, Petibon Y. PET Mapping of Receptor Occupancy Using Joint Direct Parametric Reconstruction. IEEE Transactions On Biomedical Engineering 2025, 72: 1057-1066. PMID: 39446540, PMCID: PMC11875991, DOI: 10.1109/tbme.2024.3486191.Peer-Reviewed Original ResearchCentral nervous systemReceptor occupancyLow-binding regionsPET scansSimulation resultsPreclinical in vivo experimentsDynamic PET scansPairs of baselineEstimation of receptor occupancyEstimation frameworkPET neuroimagingReconstruction frameworkModulating drugsTime activity curvesParametric reconstructionDevelopment of drugs
2024
Diffusion-based Bayesian posterior distribution prediction of kinetic parameters in dynamic PET
Djebra Y, Liu X, Marin T, Tiss A, Dhaynaut M, Guehl N, Johnson K, Fakhri G, Ma C, Ouyang J. Diffusion-based Bayesian posterior distribution prediction of kinetic parameters in dynamic PET. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10657955.Peer-Reviewed Original ResearchConditional variational autoencoderEfficient deep learning-based approachMarkov chain Monte CarloDenoising diffusion probabilistic modelDeep learning-based approachDiffusion probabilistic modelLearning-based approachApproximate posterior distributionPosterior distributionVariational autoencoderHeavy computationTau protein aggregationBayesian inferenceProbabilistic modelData-DrivenStudy molecular processesBayesian posterior distributionProtein aggregationMetropolis-Hastings Markov chain Monte CarloMolecular processesAlzheimer's diseaseNeurodegenerative diseasesKinetic parametersEstimate posterior distributionsAutoencoderPET motion correction using subspace-based real-time MR imaging in simultaneous PET/MR
Mounime I, Marin T, Han P, Ouyang J, Gori P, Angelini E, Fakhri G, Ma C. PET motion correction using subspace-based real-time MR imaging in simultaneous PET/MR. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10657647.Peer-Reviewed Original ResearchOrdered-subset expectation maximizationMotion correctionGated reconstructionsMotion-corrected PET reconstructionsPET eventsCardiac motion phasesMotion correction methodCardiac motionMotion phaseReconstructed dynamic imagesPET reconstructionReal-time MR imagingSimultaneous PET/MRPatient motionSoft tissue contrastDynamic MR image reconstructionReference phaseMitigate artifactsLow-rank propertyMR image reconstructionPositron emission tomographyManifold learning frameworkSpatial resolutionBlurring artifactsImage reconstructionDIANA - Detectability Investgations using Artificial Nodal Additions
Bayerlein R, Xia M, Xie H, Spencer B, Ouyang J, Fakhri G, Nardo L, Liu C, Badawi R. DIANA - Detectability Investgations using Artificial Nodal Additions. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10657528.Peer-Reviewed Original ResearchContrast recovery coefficientContrast-to-noise ratioLesion-to-background ratioList-mode dataTotal-body PET/CT scannerPositron emission tomographyContrast recoveryOSEM algorithmPatient motionPET/CT scannerArtificial lesionsImage quality metricsLesion detectionQuantitative accuracyPositron emission tomography scanRecovery coefficientCount densityImage contrastBody mass indexImage noisePositron emission tomography imaging techniquesFrame lengthImage smoothingActivity concentrationsAccuracy of lesion detectionAnatomically and Metabolically Informed Deep Learning Low-Count PET Image Denoising
Xia M, Xie H, Liu Q, Guo L, Ouyang J, Bayerlein R, Spencer B, Badawi R, Li Q, Fakhri G, Liu C. Anatomically and Metabolically Informed Deep Learning Low-Count PET Image Denoising. 2024, 00: 1-2. DOI: 10.1109/nss/mic/rtsd57108.2024.10657099.Peer-Reviewed Original ResearchDeep learningOver-smoothed imagesDL training processesHigh-count imagesImage denoisingDenoised imageLow-count dataSemantic informationSemantic classesSegmentation guidanceTraining processPET/CT systemHistogram distributionImage qualitySegmentation toolPositron emission tomographyImagesDenoisingDatasetHistogramPriorsRadiation exposurePoint-supervised Brain Tumor Segmentation with Box-prompted Medical Segment Anything Model
Liu X, Woo J, Ma C, Ouyang J, Fakhri G. Point-supervised Brain Tumor Segmentation with Box-prompted Medical Segment Anything Model. 2011 IEEE Nuclear Science Symposium Conference Record 2024, 00: 1-1. PMID: 39445308, PMCID: PMC11497479, DOI: 10.1109/nss/mic/rtsd57108.2024.10656071.Peer-Reviewed Original ResearchAblation Study of Diffusion Model with Transformer Backbone for Low-count PET Denoising
Huang Y, Liu X, Miyazaki T, Omachi S, Fakhri G, Ouyang J. Ablation Study of Diffusion Model with Transformer Backbone for Low-count PET Denoising. 2011 IEEE Nuclear Science Symposium Conference Record 2024, 00: 1-2. PMID: 39445309, PMCID: PMC11497477, DOI: 10.1109/nss/mic/rtsd57108.2024.10655179.Peer-Reviewed Original ResearchIR tasksImage restorationImage super-resolution taskField of image restorationSuper-resolution taskLatent feature spaceConventional UNetDenoising iterationDenoising taskTransformer backboneDenoising AutoencoderTexture restorationVision TransformerFeature spaceAblation studiesLearning schemeBackbone networkImage generationDenoisingUNetIR modelPSNRSpatial informationAutoencoderTask