2022
Posterior estimation using deep learning: a simulation study of compartmental modeling in dynamic positron emission tomography
Liu X, Marin T, Amal T, Woo J, Fakhri G, Ouyang J. Posterior estimation using deep learning: a simulation study of compartmental modeling in dynamic positron emission tomography. Medical Physics 2022, 50: 1539-1548. PMID: 36331429, PMCID: PMC10087283, DOI: 10.1002/mp.16078.Peer-Reviewed Original ResearchMeSH KeywordsBayes TheoremComputer SimulationDeep LearningNeural Networks, ComputerPositron-Emission TomographyConceptsConditional variational auto-encoderDeep learning approachNeural networkDeep learningMarkov chain Monte CarloVariational Bayesian inference frameworkLearning approachDeep learning-based approachVariational auto-encoderDeep neural networksLearning-based approachDynamic brain PET imagingPosterior distributionEstimate posterior distributionsBayesian inference frameworkAuto-encoderMedical imagesInference frameworkNetworkSimulation studyBrain PET imagingLearningPosterior estimatesInferior performanceImagesAutomation of generative adversarial network-based synthetic data-augmentation for maximizing the diagnostic performance with paranasal imaging
Kong H, Kim J, Moon H, Park H, Kim J, Lim R, Woo J, Fakhri G, Kim D, Kim S. Automation of generative adversarial network-based synthetic data-augmentation for maximizing the diagnostic performance with paranasal imaging. Scientific Reports 2022, 12: 18118. PMID: 36302815, PMCID: PMC9613909, DOI: 10.1038/s41598-022-22222-z.Peer-Reviewed Original ResearchConceptsSynthetic data augmentationData augmentationLack of training dataConventional data augmentationDeep learning methodsTraining dataLearning methodsPipeline approachAlgorithm trainingGraphical dataAutomationWaters' view radiographsModel performanceAutomated pipelinePerformancePerformance parametersAlgorithmDatasetAugmentationDataMethodPipelineRulesIndustrial workers
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 ResearchConceptsStructural 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 PETDeep learning-based GTV contouring modeling inter- and intra- observer variability in sarcomas
Marin T, Zhuo Y, Lahoud R, Tian F, Ma X, Xing F, Moteabbed M, Liu X, Grogg K, Shusharina N, Woo J, Lim R, Ma C, Chen Y, El Fakhri G. Deep learning-based GTV contouring modeling inter- and intra- observer variability in sarcomas. Radiotherapy And Oncology 2021, 167: 269-276. PMID: 34808228, PMCID: PMC8934266, DOI: 10.1016/j.radonc.2021.09.034.Peer-Reviewed Original ResearchConceptsGross tumor volumeRadiation therapy treatment planningGross tumor volume contoursGross tumor volume delineationTherapy treatment planningIntra-observer variabilityConsensus contoursGTV contoursPre-operative CT imagesSoft tissue sarcomasRadiation oncologistsTumor volumeBone sarcomasTreatment planningAccurate contoursCT imagesDelineation procedureSarcomaSoft tissueConfidence levelRadiationPatientsHausdorff distanceMultiple contoursX-rayDetecting lumbar lesions in 99mTc‐MDP SPECT by deep learning: Comparison with physicians
Petibon Y, Fahey F, Cao X, Levin Z, Sexton‐Stallone B, Falone A, Zukotynski K, Kwatra N, Lim R, Bar‐Sever Z, Chemli Y, Treves S, Fakhri G, Ouyang J. Detecting lumbar lesions in 99mTc‐MDP SPECT by deep learning: Comparison with physicians. Medical Physics 2021, 48: 4249-4261. PMID: 34101855, DOI: 10.1002/mp.15033.Peer-Reviewed Original ResearchConceptsSingle-photon emission computed tomographyLow back painLumbar lesionsPediatric patientsTc-MDPEvaluate low back painCause of low back painTc-MDP scanLesion-presentEmission computed tomographyConvolutional neural networkClinical likelihoodBack painInterreader variabilityDeep convolutional neural networkLumbar locationLesionsStress lesionsFocal lesionsDeep learningPatientsLumbar stressPhysiciansDL systemsLROC studiesMagnetic 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
Attenuation 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 ResearchConceptsAttenuation 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 performance
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 resolutionDifferentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning
Woo J, Xing F, Prince J, Stone M, Green J, Goldsmith T, Reese T, Wedeen V, Fakhri G. Differentiating post-cancer from healthy tongue muscle coordination patterns during speech using deep learning. The Journal Of The Acoustical Society Of America 2019, 145: el423-el429. PMID: 31153323, PMCID: PMC6530633, DOI: 10.1121/1.5103191.Peer-Reviewed Original ResearchMeSH KeywordsDeep LearningFacial MusclesHumansMagnetic Resonance ImagingMovementNeoplasmsNeural Networks, ComputerSpeechTongue
2018
Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting
Kim K, Wu D, Gong K, Dutta J, Kim J, Son Y, Kim H, Fakhri G, Li Q. Penalized PET Reconstruction Using Deep Learning Prior and Local Linear Fitting. IEEE Transactions On Medical Imaging 2018, 37: 1478-1487. PMID: 29870375, PMCID: PMC6375088, DOI: 10.1109/tmi.2018.2832613.Peer-Reviewed Original ResearchConceptsDeep learningDenoising convolutional neural networkConvolutional neural networkDeep learning-basedPerformance of iterative reconstructionPotential of deep learningDeep networksNoise levelLearning-basedReconstruction frameworkDegradation of performanceNeural networkDnCNNMedical imagesDownsampled dataFitness functionPoisson thinningFull-dose imagesLow dose imagesNoise conditionsNetworkImage qualityPET reconstructionDose imagesDeep