2024
Accelerated 3D metabolite T1 mapping of the brain using variable‐flip‐angle SPICE
Zhao Y, Li Y, Guo R, Jin W, Sutton B, Ma C, Fakhri G, Li Y, Luo J, Liang Z. Accelerated 3D metabolite T1 mapping of the brain using variable‐flip‐angle SPICE. Magnetic Resonance In Medicine 2024, 92: 1310-1322. PMID: 38923032, DOI: 10.1002/mrm.30200.Peer-Reviewed Original ResearchMeSH KeywordsAdultAlgorithmsBrainBrain MappingFemaleHumansImage Processing, Computer-AssistedImaging, Three-DimensionalMagnetic Resonance ImagingMagnetic Resonance SpectroscopyMalePhantoms, ImagingReproducibility of ResultsConceptsLow-rank tensor modelGeneralized series modelMetabolite TExperimental resultsBrain metabolitesClinically acceptable scan timeEfficient encodingPhantom experimental resultsAcceptable scan timeNoisy dataSparse samplingImaging problemsData processingHealthy subject dataVariable flip angleFlip angleTensor modelSaturation effectsQuantitative metabolic imagingMRSI techniquePhantomScan timeData acquisitionMetabolic imagingT1 mapping
2023
PET image denoising based on denoising diffusion probabilistic model
Gong K, Johnson K, El Fakhri G, Li Q, Pan T. PET image denoising based on denoising diffusion probabilistic model. European Journal Of Nuclear Medicine And Molecular Imaging 2023, 51: 358-368. PMID: 37787849, PMCID: PMC10958486, DOI: 10.1007/s00259-023-06417-8.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsHumansImage Processing, Computer-AssistedModels, StatisticalPositron-Emission TomographySignal-To-Noise RatioConceptsDenoising diffusion probabilistic modelPET image denoisingDiffusion probabilistic modelImage denoisingDenoising methodNonlocal meansNetwork inputGenerative adversarial networkData consistency constraintsProbabilistic modelLearning-based modelsAdversarial networkData distributionDenoisingRefinement stepsIterative refinementFlexible frameworkImage qualityPhysical degrading factorsUNetNetworkDatasetImagesInputNoise levelAttentive continuous generative self-training for unsupervised domain adaptive medical image translation
Liu X, Prince J, Xing F, Zhuo J, Reese T, Stone M, El Fakhri G, Woo J. Attentive continuous generative self-training for unsupervised domain adaptive medical image translation. Medical Image Analysis 2023, 88: 102851. PMID: 37329854, PMCID: PMC10527936, DOI: 10.1016/j.media.2023.102851.Peer-Reviewed Original ResearchMeSH KeywordsAnisotropyBayes TheoremHumansImage Processing, Computer-AssistedLearningReproducibility of ResultsUncertaintyConceptsUnsupervised domain adaptationImage translationProblem of domain shiftSelf-trainingImage modality translationLabeled source domainTarget domain dataSelf-attention schemeAlternating optimization schemeHeterogeneous target domainContinuous value predictionPseudo-labelsDomain adaptationUDA methodsDomain shiftSoftmax probabilitiesSource domainTarget domainVariational BayesBackground regionsTranslation tasksTraining processDomain dataGeneration taskOptimization schemeImpact of motion correction on [18F]-MK6240 tau PET imaging
Tiss A, Marin T, Chemli Y, Spangler-Bickell M, Gong K, Lois C, Petibon Y, Landes V, Grogg K, Normandin M, Becker A, Thibault E, Johnson K, Fakhri G, Ouyang J. Impact of motion correction on [18F]-MK6240 tau PET imaging. Physics In Medicine And Biology 2023, 68: 105015. PMID: 37116511, PMCID: PMC10278956, DOI: 10.1088/1361-6560/acd161.Peer-Reviewed Original ResearchMeSH KeywordsAgedAlzheimer DiseaseBrainHumansImage Processing, Computer-AssistedMotionPositron-Emission TomographyConceptsMotion correctionPET quantitationImpact of motion correctionList-mode reconstructionMotion correction methodList-mode dataMotion-corrected imagesEffect of motion correctionVoxel displacementsPhantom experimentsOptical tracking dataLong acquisitionBrain PET scansSlow motionImage qualityPET imagingPositron emission tomographyCorrectionMotionCorrection methodRates of tau accumulationHead motionMotion metricsPhantomPositronArterial spin labeled perfusion imaging with balanced steady-state free precession readout and radial sampling
Han P, Marin T, Zhuo Y, Ouyang J, El Fakhri G, Ma C. Arterial spin labeled perfusion imaging with balanced steady-state free precession readout and radial sampling. Magnetic Resonance Imaging 2023, 102: 126-132. PMID: 37187264, PMCID: PMC10524790, DOI: 10.1016/j.mri.2023.05.005.Peer-Reviewed Original ResearchMeSH KeywordsArteriesBrainImage Processing, Computer-AssistedImaging, Three-DimensionalMagnetic Resonance ImagingPerfusionPerfusion ImagingSpin LabelsConceptsOff-resonance effectsBalanced steady-state free precessionPhase-cycling techniqueTemporal SNRBalanced steady-state free precession acquisitionRadial sampling schemeSpoiled gradient-recalled acquisitionRadial samplingCartesian sampling schemeBalanced steady-state free precession readoutK-space dataSampling schemeSpin labelingSteady-state free precessionK-spaceImage readoutBanding artifactsMotion-related artifactsReadoutFree precessionArterial spin labelingImage reconstructionParallel imagingImaging timePerfusion-weighted imagingSuper-resolution in brain positron emission tomography using a real-time motion capture system
Chemli Y, Tétrault M, Marin T, Normandin M, Bloch I, El Fakhri G, Ouyang J, Petibon Y. Super-resolution in brain positron emission tomography using a real-time motion capture system. NeuroImage 2023, 272: 120056. PMID: 36977452, PMCID: PMC10122782, DOI: 10.1016/j.neuroimage.2023.120056.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsAnimalsBrainImage Processing, Computer-AssistedMotionMotion CapturePhantoms, ImagingPositron Emission Tomography Computed TomographyPositron-Emission TomographyConceptsBrain positron emission tomographySuper-resolutionEvent-by-event basisReal-time motion capture systemSR reconstruction methodTracking cameraVisualization of small structuresPET reconstruction algorithmMoving phantomMeasure target motionLine profilesPET/CT scannerMeasured shiftsImprove image resolutionMotion capture systemMotion tracking devicePositron emission tomographyReconstruction algorithmSpatial resolutionMeasured linesPhantomReal-timeEstimation frameworkIncreased spatial resolutionReconstruction method
2022
Manifold Learning via Linear Tangent Space Alignment (LTSA) for Accelerated Dynamic MRI With Sparse Sampling
Djebra Y, Marin T, Han P, Bloch I, Fakhri G, Ma C. Manifold Learning via Linear Tangent Space Alignment (LTSA) for Accelerated Dynamic MRI With Sparse Sampling. IEEE Transactions On Medical Imaging 2022, 42: 158-169. PMID: 36121938, PMCID: PMC10024645, DOI: 10.1109/tmi.2022.3207774.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsComputer SimulationImage Processing, Computer-AssistedMagnetic Resonance ImagingModels, TheoreticalConceptsSpace alignmentSampled k-space dataState-of-the-art methodsIntrinsic low-dimensional manifold structureNumerical simulation studyLow-dimensional manifold structureState-of-the-artLinear subspace modelSparsity modelModel-based frameworkSubspace modelManifold structureMathematical modelManifold modelSparse samplingImage reconstructionMRI applicationsDynamic magnetic resonance imagingSpatiotemporal signalsSpatial resolutionPerformanceSimulation studyImagesMethodSparsityBrain MR Atlas Construction Using Symmetric Deep Neural Inpainting
Xing F, Liu X, Kuo C, Fakhri G, Woo J. Brain MR Atlas Construction Using Symmetric Deep Neural Inpainting. IEEE Journal Of Biomedical And Health Informatics 2022, 26: 3185-3196. PMID: 35139030, PMCID: PMC9250592, DOI: 10.1109/jbhi.2022.3149754.Peer-Reviewed Original ResearchConceptsImage inpainting methodInpainting methodDeep learning-based image inpainting methodsBrain Tumor Segmentation ChallengeMultimodal Brain Tumor Segmentation ChallengeReduce reconstruction errorAtlas constructionStatistical brain atlasInpainted regionsInpainted dataImage registration methodReconstruction errorTumor regionMutual informationSimilarity scoresSegmentation ChallengeSymmetry constraintsImage dataRegistration methodMagnetic resonance imagingTumor locationStatistical atlasDistribution of lesionsCross-correlationPatient population
2021
A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET
Xue S, Guo R, Bohn K, Matzke J, Viscione M, Alberts I, Meng H, Sun C, Zhang M, Zhang M, Sznitman R, El Fakhri G, Rominger A, Li B, Shi K. A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET. European Journal Of Nuclear Medicine And Molecular Imaging 2021, 49: 1843-1856. PMID: 34950968, PMCID: PMC9015984, DOI: 10.1007/s00259-021-05644-1.Peer-Reviewed Original ResearchMeSH KeywordsArtificial IntelligenceBrainDeep LearningFluorodeoxyglucose F18HumansImage Processing, Computer-AssistedPositron-Emission TomographyConceptsStructural similarity index measurePET imagingGenerative adversarial networkNuclear medicine physiciansArtificial intelligenceLow-dose scansBaseline image qualityDose reductionConditional generative adversarial networkClinical imaging assessmentSimilarity index measureDiversity of clinical practiceDevelopment of AI technologyDeep learning developmentDose acquisitionImaging assessmentMedicine physiciansImage qualityResultsThe improvementPatientsClinical acceptanceClinical practiceClinical settingAdversarial networkLow-dose PETSegmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI
Liu X, Xing F, Gaggin H, Wang W, Kuo C, Fakhri G, Woo J. Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2021, 00: 3535-3538. PMID: 34892002, DOI: 10.1109/embc46164.2021.9629770.Peer-Reviewed Original ResearchMeSH KeywordsHeartHeart VentriclesImage Processing, Computer-AssistedMagnetic Resonance Imaging, CineNeural Networks, ComputerConceptsConvolutional neural networkSegmentation of cardiac structuresSaab transformSubspace approximationAccurate segmentation of cardiac structuresDimension reductionConvolutional neural network modelConcatenation of featuresUnsupervised dimension reductionConditional random fieldPixel-wise classificationSupervised dimension reductionU-Net modelMachine learning modelsSubspace learningChannel-wiseSegmentation databaseSegmentation frameworkNeural networkU-NetEfficient segmentationAccurate segmentationLearning modelsCardiac MR imagesRandom fieldQuantitative PET in the 2020s: a roadmap
Meikle S, Sossi V, Roncali E, Cherry S, Banati R, Mankoff D, Jones T, James M, Sutcliffe J, Ouyang J, Petibon Y, Ma C, El Fakhri G, Surti S, Karp J, Badawi R, Yamaya T, Akamatsu G, Schramm G, Rezaei A, Nuyts J, Fulton R, Kyme A, Lois C, Sari H, Price J, Boellaard R, Jeraj R, Bailey D, Eslick E, Willowson K, Dutta J. Quantitative PET in the 2020s: a roadmap. Physics In Medicine And Biology 2021, 66: 06rm01. PMID: 33339012, PMCID: PMC9358699, DOI: 10.1088/1361-6560/abd4f7.Peer-Reviewed Original ResearchMeSH KeywordsArtificial IntelligenceHistory, 20th CenturyHistory, 21st CenturyHumansImage Processing, Computer-AssistedImaging, Three-DimensionalKineticsMedical OncologyNeoplasmsPositron Emission Tomography Computed TomographyPositron-Emission TomographyPrognosisRadiopharmaceuticalsSystems BiologyTomography, X-Ray ComputedConceptsTime-of-flight positron emission tomographyStatistical image reconstructionTotal-body positron emission tomographyPositron emission tomographyQuantitative positron emission tomographyImage reconstructionWhole-body positron emission tomographySensitivity of positron emission tomographyCapabilities of positron emission tomographyImage qualityClinical applicationTracer principleRelevant parametersOncology applicationsPhysicsStatistical qualityExpansion of applicationsEmission tomographyClinical practicePET/MRBiologically relevant parametersSensitive biomarkerPositronMagnetic resonance parameter mapping using model‐guided self‐supervised deep learning
Liu F, Kijowski R, Fakhri G, Feng L. Magnetic resonance parameter mapping using model‐guided self‐supervised deep learning. Magnetic Resonance In Medicine 2021, 85: 3211-3226. PMID: 33464652, PMCID: PMC9185837, DOI: 10.1002/mrm.28659.Peer-Reviewed Original ResearchMeSH KeywordsArtifactsDeep LearningImage Processing, Computer-AssistedMagnetic Resonance ImagingMagnetic Resonance SpectroscopyConceptsMR parameter mappingSupervised learningReconstruction qualityImaging modelSelf-supervised deep learningStandard supervised learningConventional iterative reconstructionData setsDeep learning purposesSuperior reconstruction qualityImprove reconstruction qualityQuantitative MRI applicationsUndersampled k-spacePresence of noisePhysical modeling constraintsSparsity constraintNetwork trainingReconstruction performanceDeep learningReconstruction frameworkMap extractionImprove image qualitySuppress noiseGround truthUndersampling artifacts
2020
Motion correction for PET data using subspace-based real-time MR imaging in simultaneous PET/MR
Marin T, Djebra Y, Han P, Chemli Y, Bloch I, Fakhri G, Ouyang J, Petibon Y, Ma C. Motion correction for PET data using subspace-based real-time MR imaging in simultaneous PET/MR. Physics In Medicine And Biology 2020, 65: 235022. PMID: 33263317, PMCID: PMC7985095, DOI: 10.1088/1361-6560/abb31d.Peer-Reviewed Original ResearchMeSH KeywordsArtifactsHumansImage Processing, Computer-AssistedMagnetic Resonance ImagingMovementMultimodal ImagingPositron-Emission TomographyTime FactorsConceptsPositron emission tomography reconstructionMotion-corrected PET reconstructionsPET reconstructionMotion-corrected PET imagesIrregular respiratory motionMotion fieldMotion correction methodMotion correction approachIrregular motion patternsUndersampled k-space dataImage quality of positron emission tomographyQuality of positron emission tomographyMotion patternsLow-rank characteristicsRespiratory motionContrast-to-noise ratioEstimated motion fieldSurrogate signalsMotion correctionK-space dataImage qualityReal-time MR imagingSimultaneous PET/MRMotion artifact reductionPET/MR scannersAttenuation correction using deep Learning and integrated UTE/multi-echo Dixon sequence: evaluation in amyloid and tau PET imaging
Gong K, Han P, Johnson K, El Fakhri G, Ma C, Li Q. Attenuation correction using deep Learning and integrated UTE/multi-echo Dixon sequence: evaluation in amyloid and tau PET imaging. European Journal Of Nuclear Medicine And Molecular Imaging 2020, 48: 1351-1361. PMID: 33108475, PMCID: PMC8411350, DOI: 10.1007/s00259-020-05061-w.Peer-Reviewed Original ResearchMeSH KeywordsDeep LearningHumansImage Processing, Computer-AssistedMagnetic Resonance ImagingMultimodal ImagingPositron-Emission TomographyTomography, X-Ray ComputedConceptsAttenuation correctionResultsThe Dice coefficientPseudo-CT imagesMR-based AC methodsAccurate ACAC accuracyPET imagingDice coefficientQuantitative accuracyAtlas methodAC methodGradient echoNear verticesTau imagingTau PET imagingAlzheimer's diseaseUltrashortCorrectionTau pathologyRapid acquisitionDeep learning methodsMonitoring of Alzheimer’s diseasePET/MRAmyloidHigh-performance rapid MR parameter mapping using model-based deep adversarial learning
Liu F, Kijowski R, Feng L, El Fakhri G. High-performance rapid MR parameter mapping using model-based deep adversarial learning. Magnetic Resonance Imaging 2020, 74: 152-160. PMID: 32980503, PMCID: PMC7669737, DOI: 10.1016/j.mri.2020.09.021.Peer-Reviewed Original ResearchMeSH KeywordsBrainDeep LearningHumansImage Processing, Computer-AssistedKneeMagnetic Resonance ImagingTime FactorsConceptsConvolutional neural networkMR parameter mappingAdversarial learningState-of-the-art reconstruction methodsEnd-to-end convolutional neural networkUndersampled k-space dataConvolutional neural network approachAdversarial learning approachState-of-the-artStructural similarity indexImage reconstruction frameworkEnd-to-endImage sharpnessData consistencyConventional reconstruction approachesReconstruction approachK-space dataImprove image sharpnessImage reconstruction approachEstimated parameter mapsImage sparsityTexture restorationNetwork trainingImage datasetsReconstruction performanceAccelerated J‐resolved 1H‐MRSI with limited and sparse sampling of (‐space
Tang L, Zhao Y, Li Y, Guo R, Clifford B, Fakhri G, Ma C, Liang Z, Luo J. Accelerated J‐resolved 1H‐MRSI with limited and sparse sampling of (‐space. Magnetic Resonance In Medicine 2020, 85: 30-41. PMID: 32726510, PMCID: PMC7992196, DOI: 10.1002/mrm.28413.Peer-Reviewed Original ResearchMR‐based PET attenuation correction using a combined ultrashort echo time/multi‐echo Dixon acquisition
Han P, Horng D, Gong K, Petibon Y, Kim K, Li Q, Johnson K, Fakhri G, Ouyang J, Ma C. MR‐based PET attenuation correction using a combined ultrashort echo time/multi‐echo Dixon acquisition. Medical Physics 2020, 47: 3064-3077. PMID: 32279317, PMCID: PMC7375929, DOI: 10.1002/mp.14180.Peer-Reviewed Original ResearchMeSH KeywordsHumansImage Processing, Computer-AssistedMagnetic Resonance ImagingPhantoms, ImagingPositron-Emission TomographyTomography, X-Ray ComputedConceptsLinear attenuation coefficientPositron emission tomography attenuation correctionPhysical compartmental modelAttenuation correctionShort T<sub>2</sub> componentPET attenuation correctionRadial k-space trajectoryMagnetic resonance (MR)-based methodK-space trajectoriesRadial trajectoryK-spaceAttenuation coefficientDixon acquisitionsPositron emission tomographyWhole white matterMuting methodImage reconstructionImaging speedMR signalMRAC methodPositron emission tomography imagingCorrectionGray matter regionsPhantomMatter regionsPreclinical Validation of a Single-Scan Rest/Stress Imaging Technique for 13N-Ammonia Positron Emission Tomography Cardiac Perfusion Studies
Guehl N, Pelletier-Galarneau M, Wooten D, Guerrero J, Kas A, Normandin M, Fakhri G, Alpert N. Preclinical Validation of a Single-Scan Rest/Stress Imaging Technique for 13N-Ammonia Positron Emission Tomography Cardiac Perfusion Studies. Circulation Cardiovascular Imaging 2020, 13: e009407. PMID: 31959009, PMCID: PMC7205554, DOI: 10.1161/circimaging.119.009407.Peer-Reviewed Original ResearchConceptsMyocardial blood flowPerfusion imagingMyocardial perfusion imaging proceduresSCAN-ALeft anterior descending arteryDose of adenosineAbsolute myocardial blood flowStress perfusion imagingAnterior descending arteryCardiac perfusion studiesMyocardial blood flow measurementsBland-Altman analysisNonstationary kinetic modelPositron emission tomographyMeasurement of restMyocardial blood flow valuesPharmacological stressorDescending arteryPreclinical validationMyocardial blood flow estimatesSingle-scan acquisitionPerfusion studiesVariable dosesImaging sessionMicrosphere MBF measurements
2019
Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning
Gong K, Han P, Fakhri G, Ma C, Li Q. Arterial spin labeling MR image denoising and reconstruction using unsupervised deep learning. NMR In Biomedicine 2019, 35: e4224. PMID: 31865615, PMCID: PMC7306418, DOI: 10.1002/nbm.4224.Peer-Reviewed Original ResearchMeSH KeywordsBrainDeep LearningHumansImage Processing, Computer-AssistedMagnetic Resonance ImagingSignal-To-Noise RatioSpin LabelsConceptsSignal-to-noise ratioImage denoisingReconstruction frameworkDeep learning-based image denoisingDeep learning-based denoisersMR image denoisingLearning-based denoisingLow signal-to-noise ratioK-space dataNoisy imagesTraining labelsTraining pairsNetwork inputNeural networkDenoisingIn vivo experiment dataSuperior performanceImaging speedReconstruction processImage qualityLong imaging timesNetworkFrameworkImagesSpatial resolutionBody motion detection and correction in cardiac PET: Phantom and human studies
Sun T, Petibon Y, Han P, Ma C, Kim S, Alpert N, Fakhri G, Ouyang J. Body motion detection and correction in cardiac PET: Phantom and human studies. Medical Physics 2019, 46: 4898-4906. PMID: 31508827, PMCID: PMC6842053, DOI: 10.1002/mp.13815.Peer-Reviewed Original ResearchMeSH KeywordsArtifactsFluorodeoxyglucose F18HeartHumansImage Processing, Computer-AssistedMovementPhantoms, ImagingPositron-Emission TomographyConceptsList-mode dataMotion-compensated image reconstructionMotion correctionCenter of massPET list-mode dataMotion correction methodMotion detectionMotion estimationImage reconstructionPatient body motionDegrade image qualityNonrigid registrationImage qualityMotion transformationCoincident distributionBody motion detectionCardiac positron emission tomographyBack-projection techniqueCovariance matrixImage volumesBody motionPositron emission tomographyBack-projectionReference framePhantom