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-makingNetworkPatient-Specific Heart Geometry Modeling for Solid Biomechanics Using Deep Learning
Pak D, Liu M, Kim T, Liang L, Caballero A, Onofrey J, Ahn S, Xu Y, McKay R, Sun W, Gleason R, Duncan J. Patient-Specific Heart Geometry Modeling for Solid Biomechanics Using Deep Learning. IEEE Transactions On Medical Imaging 2024, 43: 203-215. PMID: 37432807, PMCID: PMC10764002, DOI: 10.1109/tmi.2023.3294128.Peer-Reviewed Original ResearchConceptsFinite element analysisDeep learning methodsSpatial accuracyElement analysisDeep learningStress estimationLearning methodsSimulation accuracyDeployment simulationHigh spatial accuracyThin structuresMesh generationVolumetric meshingDeformation energyGeometry modelingVolumetric meshMesh qualityElement qualitySimultaneous optimizationMain noveltyBiomechanics studiesMeshModeling characteristicsAccuracyDownstream analysis
2023
Teacher’s PET: Semi-supervised Deep Learning for PET Head Motion Correction
Zeng T, You C, Cai Z, Lieffrig E, Zhang J, Chen F, Lu Y, Onofrey J. Teacher’s PET: Semi-supervised Deep Learning for PET Head Motion Correction. 2023, 00: 1-1. DOI: 10.1109/nssmicrtsd49126.2023.10337834.Peer-Reviewed Original ResearchMotion tracking methodHead motion correctionMotion trackingExtra hardwareMotion estimatesTracking methodSemi-supervised deep learningSupervised deep learning methodsQuality training dataDeep learning methodsMean teacher modelSemi-supervised mannerMotion correctionMotion detectionHead motionCorrection networkDeep learningInaccurate quantitative resultsTraining dataLearning methodsBetter generalizationMotionLow resolutionCorrection resultsPerformanceSpatial Normalization to Improve Deep Learning-based Head Motion Correction in PET
Zhang J, Lieffrig E, Zeng T, You C, Cai Z, Toyonaga T, Lu Y, Onofrey J. Spatial Normalization to Improve Deep Learning-based Head Motion Correction in PET. 2023, 00: 1-1. DOI: 10.1109/nssmicrtsd49126.2023.10338387.Peer-Reviewed Original ResearchDuSFE: Dual-Channel Squeeze-Fusion-Excitation co-attention for cross-modality registration of cardiac SPECT and CT
Chen X, Zhou B, Xie H, Guo X, Zhang J, Duncan J, Miller E, Sinusas A, Onofrey J, Liu C. DuSFE: Dual-Channel Squeeze-Fusion-Excitation co-attention for cross-modality registration of cardiac SPECT and CT. Medical Image Analysis 2023, 88: 102840. PMID: 37216735, PMCID: PMC10524650, DOI: 10.1016/j.media.2023.102840.Peer-Reviewed Original ResearchConceptsCross-modality registrationConvolutional layersCo-attention mechanismMultiple convolutional layersCo-attention moduleDifferent convolutional layersMedical image registrationInput data streamDeep learning strategiesLow registration errorIntensity-based registration methodCardiac SPECTΜ-mapsDeep learningFeature fusionData streamsInput imageSource codeFeature mapsNeural networkImage registrationSpatial featuresRegistration performanceRegistration methodInput informationMulti-Task Deep Learning and Uncertainty Estimation for Pet Head Motion Correction
Lieffrig E, Zeng T, Zhang J, Fontaine K, Fang X, Revilla E, Lu Y, Onofrey J. Multi-Task Deep Learning and Uncertainty Estimation for Pet Head Motion Correction. 2011 IEEE International Symposium On Biomedical Imaging: From Nano To Macro 2023, 00: 1-5. PMID: 38111738, PMCID: PMC10725741, DOI: 10.1109/isbi53787.2023.10230791.Peer-Reviewed Original ResearchMulti-task deep learningMulti-task architectureMonte Carlo dropoutTesting subjectsDeep learningMotion tracking deviceSupervised learningMotion correction methodNetwork predictionHead motion correctionAppearance predictionReconstructed imagesPrediction performanceImage acquisitionImage qualityTracking deviceMotion correctionLearning processUncertainty estimationTomography image acquisitionHead motionPrediction uncertaintyLearningQualitative resultsArchitecture
2022
Multi-tracer Deep Learning for PET Head Motion Correction
Lieffrig E, Zeng T, Zhang J, Fang X, Revilla E, Lu Y, Onofrey J. Multi-tracer Deep Learning for PET Head Motion Correction. 2022, 00: 1-4. DOI: 10.1109/nss/mic44845.2022.10399143.Peer-Reviewed Original ResearchCamera motion trackingHead motionMotion correction performanceHead motion correctionRigid head motionContinuous head motionTransform blockFeature-wiseSupervised learningDeep learningMotion correctionBrain positron emission tomographyMotion trackingTracking hardwareExternal devicesCorrect performanceImage qualityQuantification errorsPositron emission tomographyQualitative resultsCorrection resultsLearningTracer typeMotionHardwareSupervised Deep Learning for Head Motion Correction in PET
Zeng T, Zhang J, Revilla E, Lieffrig E, Fang X, Lu Y, Onofrey J. Supervised Deep Learning for Head Motion Correction in PET. Lecture Notes In Computer Science 2022, 13434: 194-203. PMID: 38107622, PMCID: PMC10725740, DOI: 10.1007/978-3-031-16440-8_19.Peer-Reviewed Original ResearchDeep learning-based algorithmMotion tracking informationHead motion correctionNovel deep learningLearning-based algorithmMotion correctionDeep learningRegression layerEncoder layersTracking hardwareNetwork performanceSupervised mannerTracking informationAblation studiesRegistration approachCloud representationBrain positron emission tomography (PET) imagingTransformation layerDesign choicesReconstructed imagesPrediction performanceExternal devicesImage analysisTransformation parametersHead motion
2021
Weakly Supervised Deep Learning for Aortic Valve Finite Element Mesh Generation from 3D CT Images
Pak D, Liu M, Ahn S, Caballero A, Onofrey J, Liang L, Sun W, Duncan J. Weakly Supervised Deep Learning for Aortic Valve Finite Element Mesh Generation from 3D CT Images. Lecture Notes In Computer Science 2021, 12729: 637-648. DOI: 10.1007/978-3-030-78191-0_49.Peer-Reviewed Original ResearchSupervised deep learningTranscather aortic valve replacementDeep learningSegmentation labelsMesh generationCorrespondence accuracyHeavy assumptionsFinite element mesh generationMesh topologyVolumetric meshLow contrastSignificant bottleneckValve modelingProblem formulationPrediction modelModel performanceCT imagesDeformation strategyLarge amountImagesBottleneckLearningMeshFrameworkLabels
2020
Sparse Data–Driven Learning for Effective and Efficient Biomedical Image Segmentation
Onofrey JA, Staib LH, Huang X, Zhang F, Papademetris X, Metaxas D, Rueckert D, Duncan JS. Sparse Data–Driven Learning for Effective and Efficient Biomedical Image Segmentation. Annual Review Of Biomedical Engineering 2020, 22: 1-27. PMID: 32169002, PMCID: PMC9351438, DOI: 10.1146/annurev-bioeng-060418-052147.Peer-Reviewed Original Research