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
2021
Deep 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 studies
2018
Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability
Tajmir S, Lee H, Shailam R, Gale H, Nguyen J, Westra S, Lim R, Yune S, Gee M, Do S. Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability. Skeletal Radiology 2018, 48: 275-283. PMID: 30069585, DOI: 10.1007/s00256-018-3033-2.Peer-Reviewed Original ResearchConceptsBone age assessmentAutomated artificial intelligenceAI assistanceBone age radiographsConvolutional neural networkDeep learning algorithmsRoot mean square errorMean square errorPediatric radiologistsUtilization of AILearning algorithmsNeural networkArtificial intelligenceIntraclass correlation coefficientImproved performancePooled cohortRadiologist interpretationImaging studiesInter-rater variationAccuracyMetabolic disordersIncreased accuracyRadiologistsAge accuracyMeasures of accuracy