2022
Creating High Fidelity Synthetic Pelvis Radiographs Using Generative Adversarial Networks: Unlocking the Potential of Deep Learning Models Without Patient Privacy Concerns
Khosravi B, Rouzrokh P, Mickley J, Faghani S, Larson A, Garner H, Howe B, Erickson B, Taunton M, Wyles C. Creating High Fidelity Synthetic Pelvis Radiographs Using Generative Adversarial Networks: Unlocking the Potential of Deep Learning Models Without Patient Privacy Concerns. The Journal Of Arthroplasty 2022, 38: 2037-2043.e1. PMID: 36535448, DOI: 10.1016/j.arth.2022.12.013.Peer-Reviewed Original ResearchConceptsAdversarial networkSynthetic imagesDL modelsImage fidelityAssessment of image fidelityPerformance of DL modelsGenerative adversarial networkDeep learning modelsCross-institutional sharingArtificial intelligence techniquesPatient privacy concernsPotential of deep learning modelsReal imagesPrivacy concernsDL techniquesIntelligence techniquesRandom imagesLearning modelsPatient privacyPaired imagesReal radiographsData safetyPelvis imagesNetworkHigh-fidelity
2009
High-fidelity and time-driven simulation of large wireless networks with parallel processing
Lee H, Manshadi V, Cox D. High-fidelity and time-driven simulation of large wireless networks with parallel processing. IEEE Communications Magazine 2009, 47: 158-165. DOI: 10.1109/mcom.2009.4804402.Peer-Reviewed Original ResearchWireless network simulationWireless networksTime-driven simulationNetwork simulatorComplex wireless networksCo-channel interferenceRun-time performancePhysical-layer detailsWorkload partitioningCo-channelDatabase designExecution timeParallel processingMultiple processorsNetworkNumerical resultsSimulationHigh-fidelityExecutionTechniqueProcessorSynchronizationWorkloadHighspeedLinks
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply