Thibault Marin, PhD
Assistant Professor of Radiology and Biomedical ImagingCards
About
Research
Publications
2025
Predicting tumor recurrence site after reirradiation in head and neck cancer: a retrospective external validation of a published [18F]-FDG PET radiomic signature
Beddok A, Grogg K, Nioche C, Rozenblum L, Orlhac F, Calugaru V, Crehange G, Shih H, Marin T, Buvat I, El Fakhri G. Predicting tumor recurrence site after reirradiation in head and neck cancer: a retrospective external validation of a published [18F]-FDG PET radiomic signature. La Radiologia Medica 2025, 1-10. PMID: 40833475, DOI: 10.1007/s11547-025-02072-1.Peer-Reviewed Original ResearchHead and neck cancerPET radiomics signaturePositive predictive valueNeck cancerRadiomics signatureRecurrent head and neck cancerExternal cohortTumor recurrence siteDose escalationLocoregional failurePET radiomicsRecurrence siteMassachusetts General HospitalLIFEx softwareIndependent cohortRadiomic featuresOriginal cutoffPatientsPredictive valuePublished cutoffsPurposeThis studyCohortGeneral HospitalRecurrenceConclusionThe studyIn vivo 3D myocardial membrane potential mapping in humans using PET/MRI
Bijari F, Han P, Marin T, Lee W, Chemli Y, Gertsenshteyn I, Mounime I, Djebra Y, Chi D, Normandin M, Ma C, Fakhri G. In vivo 3D myocardial membrane potential mapping in humans using PET/MRI. EJNMMI Research 2025, 15: 93. PMID: 40715686, PMCID: PMC12297085, DOI: 10.1186/s13550-025-01287-7.Peer-Reviewed Original ResearchMembrane potentialExtracellular volume fraction measurementsExtracellular volume fraction mappingBolus-plus-infusion protocolT1 mapping sequencesVolume of distributionWritten Informed ConsentCardiac PET/MR imagingRigid image registrationHumans in vivoContrast agent injectionPET motion correctionFree breathingTracer volume of distributionImage registrationBolus injectionCardiac MRMitochondrial membrane potentialCardiac diseaseHealthy subjectsPET/MR imagingImaging studiesTreatment monitoringAgent injectionPET tracersBayesian 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 parametersFast 3D cardiac extracellular volume mapping and cine imaging via continuous free-breathing acquisition with mid-scan contrast agent injection
Lee W, Han P, Marin T, Mounime I, Bijari F, Normandin M, Fakhri G, Ma C. Fast 3D cardiac extracellular volume mapping and cine imaging via continuous free-breathing acquisition with mid-scan contrast agent injection. Proceedings Of The International Society For Magnetic Resonance In Medicine ... Scientific Meeting And Exhibition. 2025 DOI: 10.58530/2025/0789.Peer-Reviewed Original ResearchContrast agent injectionExtracellular volume mappingCine imagesContrast agent administrationExtracellular volumeFree-breathing scanFree-breathing acquisitionECV mapsAgent injectionAgent administrationTotal scan timeCardiac imaging methodsImage reconstructionScan timeCardiac motionSpace alignmentCineTime efficiencyModeling inter‐reader variability in clinical target volume delineation for soft tissue sarcomas using diffusion model
Dong Y, Marin T, Zhuo Y, Najem E, Beddok A, Rozenblum L, Moteabbed M, Grogg K, Xing F, Woo J, Chen Y, Lim R, Liu X, Ma C, Fakhri G. Modeling inter‐reader variability in clinical target volume delineation for soft tissue sarcomas using diffusion model. Medical Physics 2025, 52: e17865. PMID: 40317577, PMCID: PMC12424543, DOI: 10.1002/mp.17865.Peer-Reviewed Original ResearchClinical target volumeGross tumor volumeClinical target volume delineationSoft tissue sarcomasInter-reader variabilityTissue sarcomasClinical target volume contoursMagnetic resonance imagingCTV delineationTarget volume delineationComputed tomographyTreatment of soft tissue sarcomasFluorodeoxyglucose positron emission tomographyCTV contoursTarget volumeVolume delineationT1-weighted magnetic resonance imagingRadiotherapy treatmentEnergy distanceHigh Dice indexPositron emission tomographyTumor volumeMicroscopic spreadFDG-PETTreatment planningDual 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 ResearchFlexible and modular PET: Evaluating the potential of TOF‐DOI panel detectors
Razdevšek G, Fakhri G, Marin T, Dolenec R, Orehar M, Chemli Y, Gola A, Gascon D, Majewski S, Pestotnik R. Flexible and modular PET: Evaluating the potential of TOF‐DOI panel detectors. Medical Physics 2025, 52: 2845-2860. PMID: 40089973, PMCID: PMC12059530, DOI: 10.1002/mp.17741.Peer-Reviewed Original ResearchDepth of interactionLong axial field-of-viewTime-of-flightPanel detectorHigh-performance computing clusterDepth-of-interaction resolutionNoise equivalent count rateDepth-of-interaction capabilityDepth-of-interaction detectorsAxial field-of-viewImage qualityTime-of-flight (TOFDistortion-free imagesPositron emission tomography scannerLong axial fieldComputer clusterSpatial resolutionLSO crystalsImage reconstructionDetector materialCount rateGATE softwareContrast-to-noise ratioParallax errorMonte Carlo simulationsPET 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 drugsGross tumor volume confidence maps prediction for soft tissue sarcomas from multi-modality medical images using a diffusion model
Dong Y, Marin T, Zhuo Y, Najem E, Moteabbed M, Xing F, Beddok A, Lahoud R, Rozenblum L, Ding Z, Liu X, Grogg K, Woo J, Chen Y, Lim R, Ma C, Fakhri G. Gross tumor volume confidence maps prediction for soft tissue sarcomas from multi-modality medical images using a diffusion model. Physics And Imaging In Radiation Oncology 2025, 33: 100734. PMID: 40123775, PMCID: PMC11926426, DOI: 10.1016/j.phro.2025.100734.Peer-Reviewed Original ResearchGross tumor volumeSoft tissue sarcomasTissue sarcomasGross tumor volume delineationManual GTV delineationsMagnetic resonance imagingComputed tomographyFluorodeoxyglucose positron emission tomographyGTV delineationT1-weighted magnetic resonance imagingSingle-modePositron emission tomographyMulti-modal medical imagesTumor volumeIntra-reader variabilityFDG-PETTreatment planningSarcomaEmission tomographyImaging modalitiesResonance imagingDiffusion modelDice indexReader variabilityPatients
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 distributionsAutoencoder
News
News
- June 02, 2025
Zeng receives travel award for SNMMI
- March 05, 2025
PET mapping of receptor occupancy using joint direct parametric reconstruction
- February 03, 2025Source: Magnetic Resonance in Imaging
Free‐breathing 3D cardiac extracellular volume (ECV) mapping using a linear tangent space alignment (LTSA) model
- January 24, 2025
Welcome New Faculty, Fellows & Staff to Yale BIDS