2023
Anonymizing Radiographs Using an Object Detection Deep Learning Algorithm.
Khosravi B, Mickley J, Rouzrokh P, Taunton M, Larson A, Erickson B, Wyles C. Anonymizing Radiographs Using an Object Detection Deep Learning Algorithm. Radiology Artificial Intelligence 2023, 5: e230085. PMID: 38074777, PMCID: PMC10698585, DOI: 10.1148/ryai.230085.Peer-Reviewed Original ResearchConvolutional neural networkDeep learning algorithmsDe-identificationLearning algorithmsDatasets of chest radiographsImage de-identificationComputer vision modelsTwo-pass approachImage processing algorithmsPrecision-recall curveSupervised learningTransfer learningVision modelsNeural networkData sharingProcessing algorithmsIdentifying informationTest setAlgorithmDecrease false-positive ratesHealth informationFalse-positive rateDatasetAccuracyPublic release
2022
Clinical implementation of artificial intelligence in neuroradiology with development of a novel workflow-efficient picture archiving and communication system-based automated brain tumor segmentation and radiomic feature extraction
Aboian M, Bousabarah K, Kazarian E, Zeevi T, Holler W, Merkaj S, Petersen G, Bahar R, Subramanian H, Sunku P, Schrickel E, Bhawnani J, Zawalich M, Mahajan A, Malhotra A, Payabvash S, Tocino I, Lin M, Westerhoff M. Clinical implementation of artificial intelligence in neuroradiology with development of a novel workflow-efficient picture archiving and communication system-based automated brain tumor segmentation and radiomic feature extraction. Frontiers In Neuroscience 2022, 16: 860208. PMID: 36312024, PMCID: PMC9606757, DOI: 10.3389/fnins.2022.860208.Peer-Reviewed Original ResearchBrain tumor segmentationMedical imagesFeature extractionTumor segmentationRadiomic feature extractionDiagnostic workstationDeep learning-based algorithmPatient's medical imagesLearning-based algorithmFeature extraction toolImage processing algorithmsYale New Haven HealthGround truth dataImage annotationAI-segmentationAI algorithmsArtificial intelligenceEnd workflowProcessing algorithmsPicture archivingLarge datasetsLarge expertManual modificationInternal datasetManual segmentationDeep Learning for Radiographic Measurement of Femoral Component Subsidence Following Total Hip Arthroplasty
Rouzrokh P, Wyles C, Kurian S, Ramazanian T, Cai J, Huang Q, Zhang K, Taunton M, Maradit Kremers H, Erickson B. Deep Learning for Radiographic Measurement of Femoral Component Subsidence Following Total Hip Arthroplasty. Radiology Artificial Intelligence 2022, 4: e210206. PMID: 35652119, PMCID: PMC9152683, DOI: 10.1148/ryai.210206.Peer-Reviewed Original Research
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
1995
703-6 Three-dimensional Echocardiographic Delineation of Myocardial Perfusion Territories: Description of a New 3-D Image Processing Approach with a New Ultrasound Contrast Agent
Delabays A, Sugeng L, Cao Q, Magni G, Schwartz S, Pandian N. 703-6 Three-dimensional Echocardiographic Delineation of Myocardial Perfusion Territories: Description of a New 3-D Image Processing Approach with a New Ultrasound Contrast Agent. Journal Of The American College Of Cardiology 1995, 25: 39a. DOI: 10.1016/0735-1097(95)91619-9.Peer-Reviewed Original ResearchImage processing algorithmsImage processing approachProcessing algorithmsMyocardial perfusion territoriesPerfusion territoriesProcessing approachContrast enhancementHypoperfused regionsRegions of contrast enhancementEvaluation of myocardial perfusionShort-axis imagesContrast agentsPersistent opacificationExtraction softwareLV perfusionCoronary artery branchesData matrixPerfusion defectsAortic rootLV myocardiumAlgorithmMyocardial perfusionSmall dosesData acquisitionArterial branches901-38 New Image Processing, Segmentation, Extraction and Display Algorithms Allow Easier and More Versatile Dynamic Volume-rendered Three-dimensional Echocardiographic Examination: Application in Experimental and Clinical Studies
Sugeng L, Delabays A, Cao Q, Magni G, Krauss M, Pandian N. 901-38 New Image Processing, Segmentation, Extraction and Display Algorithms Allow Easier and More Versatile Dynamic Volume-rendered Three-dimensional Echocardiographic Examination: Application in Experimental and Clinical Studies. Journal Of The American College Of Cardiology 1995, 25: 14a. DOI: 10.1016/0735-1097(95)91515-y.Peer-Reviewed Original ResearchDisplay algorithmImage processing algorithmsProcessing algorithmsColor encodingClinical studiesExtraction regionAlgorithmImage projectionFiltering techniqueImage dataExtraction softwareFan-like scanningData matrixStudy of myocardial perfusionOpacification gradeEchocardiographic examinationImagesContrast administrationDisplayRegions of pathologyMyocardial perfusionSegmentsClinical potentialImaging modalities
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply