2024
Monte-Carlo Frequency Dropout for Predictive Uncertainty Estimation in Deep Learning
Zeevi T, Venkataraman R, Staib L, Onofrey J. Monte-Carlo Frequency Dropout for Predictive Uncertainty Estimation in Deep Learning. 2024, 00: 1-5. DOI: 10.1109/isbi56570.2024.10635511.Peer-Reviewed Original ResearchArtificial neural networkState-of-the-artMedical image dataPredictive uncertainty estimationBiomedical image dataImage dataOptimal artificial neural networkMC dropoutDropout approachSource-codeDrop-connectDeep learningNeural networkSignal spaceMonte-CarloPrediction uncertaintyUncertainty estimationDiverse setComprehensive comparisonPrediction scenariosDeepPosterior predictive distributionRepositoryDecision-makingNetwork
2003
Entropy-Based Dual-Portal-to-3-DCT Registration Incorporating Pixel Correlation
Bansal R, Staib LH, Chen Z, Rangarajan A, Knisely J, Nath R, Duncan JS. Entropy-Based Dual-Portal-to-3-DCT Registration Incorporating Pixel Correlation. IEEE Transactions On Medical Imaging 2003, 22: 29. PMID: 12703758, DOI: 10.1109/tmi.2002.806430.Peer-Reviewed Original ResearchConceptsRegistration frameworkImage dataMutual information-based registration algorithmRegistration parametersPortal imagesUltrasound image dataReal patient dataTomography image dataImage pixelsPixel correlationRegistration algorithmPatient setup verificationSegmentationPixel intensityMarkov random processInitial versionTransformation parametersAppropriate entropyImagesAlgorithmPatient dataFrameworkCT imagesLine processSetup verification
1996
Parameterized Feasible Boundaries in Gradient Vector Fields
Worring M, Smeulders A, Staib L, Duncan J. Parameterized Feasible Boundaries in Gradient Vector Fields. Computer Vision And Image Understanding 1996, 63: 135-144. DOI: 10.1006/cviu.1996.0009.Peer-Reviewed Original ResearchImage informationModel-based segmentation procedureObject boundariesSegmentation of imagesDirectional gradient informationLocal image informationObjective functionReal medical imagesObject of interestObject boundary extractionMedical imagesImage dataSmoothness objectiveConflicting objectsBoundary extractionComplex imagesGradient informationArtificial dataSegmentation procedureFeasible boundaryGradient magnitudeSegmentationPhysical feasibilityImagesObjectsModel-based deformable surface finding for medical images
Staib L, Duncan J. Model-based deformable surface finding for medical images. IEEE Transactions On Medical Imaging 1996, 15: 720-731. PMID: 18215953, DOI: 10.1109/42.538949.Peer-Reviewed Original Research
1993
Parameterized feasible boundaries in gradient vector fields
Worring M, Smeulders A, Staib L, Duncan J. Parameterized feasible boundaries in gradient vector fields. Lecture Notes In Computer Science 1993, 687: 48-61. DOI: 10.1007/bfb0013780.Peer-Reviewed Original ResearchObject boundariesMedical imagesModel-based segmentation procedureComplex medical imagesSegmentation of imagesDirectional gradient informationLocal image informationReal medical imagesObject of interestImage informationImage dataSmoothness objectiveConflicting objectsNew objective functionProblem of extractionGradient informationArtificial dataSegmentation procedureFeasible boundarySegmentationPhysical feasibilityImagesObjective functionObjectsGradient vector field
1989
Left ventricular analysis from cardiac images using deformable models
Staib L, Duncan J. Left ventricular analysis from cardiac images using deformable models. 1989, 427-430. DOI: 10.1109/cic.1988.72651.Peer-Reviewed Original ResearchDeformable modelImage understanding systemElliptic Fourier decompositionProbabilistic deformable modelCardiac image sequencesIntelligent segmentationSegmentation problemImage dataImage sequencesUnderstanding systemCardiac imagesOptimization problemFlexible constraintsLeft ventricular analysisIrregularity of shapeNatural objectsSegmentationQuantitative evaluationGood matchParametric modelVentricular analysisImagesSystemObjectsModelParametrically deformable contour models
Staib L, Duncan J. Parametrically deformable contour models. 2015 IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 1989, 98-103. DOI: 10.1109/cvpr.1989.37834.Peer-Reviewed Original ResearchElliptic Fourier decompositionProbabilistic deformable modelVariety of imagesDeformable contour modelSegmentation problemImage dataBoundary findingShape informationDeformable modelInitial experimentationContour modelOptimization problemFlexible constraintsIrregularity of shapeBetter resultsNatural objectsSegmentationGood matchParametric modelImagesObjectsExperimentationModelInformationConstraints