2024
Cross noise level PET denoising with continuous adversarial domain generalization
Liu X, Eslahi S, Marin T, Tiss A, Chemli Y, Huang Y, Johnson K, Fakhri G, Ouyang J. Cross noise level PET denoising with continuous adversarial domain generalization. Physics In Medicine And Biology 2024, 69: 085001. PMID: 38484401, PMCID: PMC11195012, DOI: 10.1088/1361-6560/ad341a.Peer-Reviewed Original ResearchDomain generalization techniqueDomain generalizationDenoising performanceSuperior denoising performanceLatent feature representationGeneral techniqueDistribution shiftsAdversarial trainingDenoised imageFeature representationDomain labelsDistribution divergenceNoise levelDeep learningImage spaceDenoisingPerformance degradationCore ideaNoise realizationsCD methodNoiseImage volumesPerformanceImagesPSNR
2023
Noise-Robust Sleep Staging via Adversarial Training With an Auxiliary Model
Yoo C, Liu X, Xing F, Fakhri G, Woo J, Kang J. Noise-Robust Sleep Staging via Adversarial Training With an Auxiliary Model. IEEE Transactions On Biomedical Engineering 2023, 70: 1252-1263. PMID: 36227815, DOI: 10.1109/tbme.2022.3214269.Peer-Reviewed Original ResearchConceptsProblem of domain shiftTarget networkConsumer-level devicesPre-trained modelsSleep staging performanceSevere noise levelsEfficient training approachAdversarial trainingAdversarial noiseDomain shiftAdversarial transformationsAuxiliary modelDL modelsInput perturbationsTraining modelArbitrary noiseTesting stageEnhanced robustnessNoise signalsTraining approachTest environmentExperimental resultsNoiseSleep stagesRobustness
2015
Non-Local and Motion-Based Low-Rank Regularizations for Gated CT Reconstruction
Kim K, Fakhri G, Li Q. Non-Local and Motion-Based Low-Rank Regularizations for Gated CT Reconstruction. 2015, 1-3. DOI: 10.1109/nssmic.2015.7582219.Peer-Reviewed Original ResearchLow-rank regularizationNon-local weightsRegistration matrixLow-rank propertyMulti-frame imagesHigh noiseNon-local regularizationImage patchesMotion blurring artifactsConcurrent executionIterative reconstruction algorithmBlurring artifactsMotion-basedReconstruction algorithmMotion patternsNon-localReduce noiseImage qualityLow-dose conditionsComputer simulationsMotion artifactsNoiseGated computed tomographyGated CTRegularization
2014
Myocardial Defect Detection Using PET-CT: Phantom Studies
Mananga E, Fakhri G, Schaefferkoetter J, Bonab A, Ouyang J. Myocardial Defect Detection Using PET-CT: Phantom Studies. PLOS ONE 2014, 9: e88200. PMID: 24505429, PMCID: PMC3914931, DOI: 10.1371/journal.pone.0088200.Peer-Reviewed Original ResearchConceptsMyocardial defect detectionFiltered back projectionChannelized Hotelling observerPhantom studyActivity distributionSubset expectation maximizationDefect detectionCardiac PET studiesMyocardial defectsHotelling observerNoise levelBack-projectionPET-CTPhantomExpectation maximizationOP-OSEMReconstruction schemePET studiesOSEMDefectsNoise
2013
Matched Signal Detection on Graphs: Theory and Application to Brain Network Classification
Hu C, Cheng L, Sepulcre J, El Fakhri G, Lu Y, Li Q. Matched Signal Detection on Graphs: Theory and Application to Brain Network Classification. Lecture Notes In Computer Science 2013, 23: 1-12. PMID: 24683953, DOI: 10.1007/978-3-642-38868-2_1.Peer-Reviewed Original ResearchMeSH KeywordsAlgorithmsAlzheimer DiseaseAniline CompoundsBenzothiazolesBrainBrain MappingConnectomeHumansImage EnhancementImage Interpretation, Computer-AssistedNerve NetNeural PathwaysPattern Recognition, AutomatedPositron-Emission TomographyReproducibility of ResultsSensitivity and SpecificityThiazolesTissue DistributionConceptsBrain network classificationNetwork classification problemWeighted energy detectorPrinciple component analysisSub-manifold structureTraditional principle component analysisSubspace detectionTraining dataEnergy detectorGraph structureProblem of Alzheimer's diseaseGraph LaplacianNetwork classificationNoise varianceLevel of smoothnessWeighted graphSignal detectionIntrinsic structureSignal modelGraphSubspaceIsing modelNoiseSignal variationsComponent analysis