2024
Integration of a continuously varying image-space PSF for a dual-panel ultra-high TOF-PET scanner
Chemli Y, Marin T, Orehar M, Dolenec R, Normandin M, Gascón D, Gola A, Grogg K, Pavón G, Razdevsek G, Pestotnik R, Fakhri G. Integration of a continuously varying image-space PSF for a dual-panel ultra-high TOF-PET scanner. 2024, 00: 1-1. DOI: 10.1109/nss/mic/rtsd57108.2024.10656225.Peer-Reviewed Original ResearchGaussian mixture modelGaussian process regressionPoint spread functionAccurate image reconstructionMaximum likelihood estimation maximizationShift-variant convolutionsImage reconstructionMixture modelProcess regressionEstimation maximizationTime-of-flight (TOFPanel architectureSpread functionArchitectureParameter interpolationHigh resolution time-of-flight (TOFTOF-PET scannerBrain phantomFitting processPositron emission tomography scannerSimulated point sourcesConvolutionAlgorithmEffective diagnosisSize benefits
2022
Automation 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
2019
MAPEM-Net: an unrolled neural network for Fully 3D PET image reconstruction
Gong K, Wu D, Kim K, Yang J, Sun T, Fakhri G, Seo Y, Li Q. MAPEM-Net: an unrolled neural network for Fully 3D PET image reconstruction. Proceedings Of SPIE--the International Society For Optical Engineering 2019, 11072: 110720o-110720o-5. DOI: 10.1117/12.2534904.Peer-Reviewed Original ResearchPET image reconstructionNeural networkImage reconstructionImage denoising applicationDeep neural networksNeural network frameworkConvolutional neural networkDenoising applicationsDenoising methodNetwork frameworkUpdate stepData consistencyIll-posedNetworkClinical datasetsInverse problemMAPEMFrameworkAlgorithmDatasetDetected photonsReconstructionMethodSimulationEMnet: an unrolled deep neural network for PET image reconstruction
Gong K, Wu D, Kim K, Yang J, Fakhri G, Seo Y, Li Q. EMnet: an unrolled deep neural network for PET image reconstruction. Progress In Biomedical Optics And Imaging 2019, 10948: 1094853-1094853-6. DOI: 10.1117/12.2513096.Peer-Reviewed Original ResearchDeep neural networksPET image reconstructionNeural networkExpectation maximizationImage reconstructionImage denoising applicationNeural network frameworkNeural network denoisersDenoising applicationsDenoising methodNetwork denoisingNetwork trainingNetwork frameworkWhole graphUpdate stepData consistencyIll-posedNetworkInverse problemEMNETDenoisingSimulated dataFrameworkAlgorithmGraph
2018
Deep networks in identifying CT brain hemorrhage
Helwan A, El-Fakhri G, Sasani H, Uzun Ozsahin D. Deep networks in identifying CT brain hemorrhage. Journal Of Intelligent & Fuzzy Systems 2018, Preprint: 1-1. DOI: 10.3233/jifs-172261.Peer-Reviewed Original ResearchConvolutional neural networkStacked autoencoderDeep networksMedical image classificationDeep learning algorithmsMedical expert's experienceImage classificationTraining timeLearning algorithmsNeural networkAutoencoderExpert experienceBrain CT imagesCT imagesNetworkHigher accuracyLess errorAlgorithmImagesAccuracyErrorClassification
2016
Dual-Energy CT Reconstruction Using Guided Image Filtering
Yang H, Kim K, Fakhri G, Kang K, Xing Y, Li Q. Dual-Energy CT Reconstruction Using Guided Image Filtering. 2016, 1-4. DOI: 10.1109/nssmic.2016.8069594.Peer-Reviewed Original ResearchGuided image filterDual-energy CT reconstructionImage filteringX-ray spectraEdge-preserving smoothingImage filtering algorithmReduce beam hardening artifactsCT reconstruction methodCT reconstructionReconstruction methodBeam hardening artifactsImage reconstruction methodImage processing algorithmsLow energyOrdered subsets algorithmDual-energy CTGuided image filtering algorithmConvergence speedProcessing algorithmsDual-energy computed tomographyAttenuation measurementsEarly iterationsFiltering algorithmDual-energyAlgorithm
2015
Fast Estimation of Image Variance for Time-of-flight PET Reconstruction
Wang M, Hu G, Fakhri G, Zhang H, Li Q. Fast Estimation of Image Variance for Time-of-flight PET Reconstruction. 2015, 1-4. DOI: 10.1109/nssmic.2015.7582040.Peer-Reviewed Original ResearchImage varianceMaximum likelihood expectation maximizationTOF-PETAhstract-The useLikelihood expectation maximizationFast algorithmExpectation maximizationReduction of computation timeComputation timeImage qualityMonte Carlo simulationsUniform diskFast estimationAlgorithmAnalytical expressionsCarlo simulationsVariance predictionImagesPET imagingPositron emission tomographyPhantomMaximization
2014
Sparse-View Spectral CT Reconstruction Using Spectral Patch-Based Low-Rank Penalty
Kim K, Ye J, Worstell W, Ouyang J, Rakvongthai Y, Fakhri G, Li Q. Sparse-View Spectral CT Reconstruction Using Spectral Patch-Based Low-Rank Penalty. IEEE Transactions On Medical Imaging 2014, 34: 748-760. PMID: 25532170, DOI: 10.1109/tmi.2014.2380993.Peer-Reviewed Original ResearchConceptsLow-rank penaltySelf-similarity of patchesLog-likelihoodPoisson log-likelihoodCost functionSpectral CT reconstructionOriginal cost functionGPU implementationAlternating minimizationSensitive to intensity changesConventional algorithmsSpectral imagingEdge directionComputational costProcedure algorithmComputational advantagesAlgorithmX-ray transmissionComputer simulationsOptimization methodSpectral computed tomographySelf-similarityCT reconstructionX-rayGPUTof-Pet Ordered Subset Reconstruction Using Non-Uniform Separable Quadratic Surrogates Algorithm
Kim K, Ye J, Cheng L, Ying K, Fakhri G, Li Q. Tof-Pet Ordered Subset Reconstruction Using Non-Uniform Separable Quadratic Surrogates Algorithm. 2014, 963-966. DOI: 10.1109/isbi.2014.6868032.Peer-Reviewed Original ResearchSignal-to-noise ratioQuadratic surrogatesTOF-basedAlgorithm timeNoise ratioReconstruction algorithmReconstructed imagesAlgorithmConvergence rateImage qualityPET reconstructionTransmission reconstructionComputer simulationsTOF PET reconstructionTOF-PETEmission reconstructionAccurate imagingImagesSmall regionConvergenceComputerReconstructionNon-uniformityOSEM