2024
Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
Zhang X, Pak D, Ahn S, Li X, You C, Staib L, Sinusas A, Wong A, Duncan J. Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration. Lecture Notes In Computer Science 2024, 15002: 651-661. DOI: 10.1007/978-3-031-72069-7_61.Peer-Reviewed Original ResearchUnsupervised registrationReal-world medical imagesCollaborative training strategyMedical image datasetsDeep learning methodsAccurate displacement estimationSignal-to-noise ratioImage datasetsRegistration architectureLearning methodsMedical imagesTraining strategyNoise distributionUncertainty estimationWeighting schemeRegistration performanceSpatial domainEstimation frameworkInput-dependentUncertainty estimation frameworkUniform noise levelsDisplacement estimationFrameworkNoise levelUnsupervisedAdaptive Correspondence Scoring for Unsupervised Medical Image Registration
Zhang X, Stendahl J, Staib L, Sinusas A, Wong A, Duncan J. Adaptive Correspondence Scoring for Unsupervised Medical Image Registration. Lecture Notes In Computer Science 2024, 15096: 76-92. DOI: 10.1007/978-3-031-72920-1_5.Peer-Reviewed Original ResearchMedical image registrationAdaptation frameworkMedical image datasetsUnsupervised learning schemeAdaptive training schemeImage registrationError residualsSupervision signalsLearning schemeImage datasetsRegistration architectureIntensity constancyScore mapNoisy gradientsMedical imagesTraining schemeImage reconstructionPerformance degradationLambertian assumptionCorrespondence scoresLoss of correspondenceTraining objectivesDisplacement estimationImage acquisitionSchemeMine Your Own Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels
You C, Dai W, Liu F, Min Y, Dvornek N, Li X, Clifton D, Staib L, Duncan J. Mine Your Own Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels. IEEE Transactions On Pattern Analysis And Machine Intelligence 2024, PP: 1-16. PMID: 39269798, DOI: 10.1109/tpami.2024.3461321.Peer-Reviewed Original ResearchMedical image segmentationImage segmentationMedical image segmentation frameworkContext of medical image segmentationLong-tailed class distributionStrong data augmentationsIntra-class variationsSemi-supervised settingData imbalance issueImage segmentation frameworkMedical image analysisMedical image dataSupervision signalsContrastive learningBenchmark datasetsUnsupervised mannerLabel setsData augmentationSegmentation frameworkDomain expertisePseudo-codeImbalance issueModel trainingMedical imagesSegmentation modelCoordinate-Independent 3-D Ultrasound Principal Stretch and Direction Imaging
Jeng G, Chen P, Hsieh M, Liu Z, Langdon J, Ahn S, Staib L, Stendahl J, Thorn S, Sinusas A, Duncan J, O'Donnell M. Coordinate-Independent 3-D Ultrasound Principal Stretch and Direction Imaging. IEEE Transactions On Biomedical Engineering 2024, PP: 1-12. PMID: 38941195, DOI: 10.1109/tbme.2024.3420220.Peer-Reviewed Original ResearchPrincipal stretchesAxial displacement componentsSpeckle tracking methodSpeckle tracking approachTracking methodRobust filterDisplacement componentsTissue incompressibilityDisplacement estimationStrain componentsDisplacement gradientsStrain informationLocalized diseased regionStrain imagingLagrangian strainLeast-squares methodTracking approachTracking frameworkCoordinate systemCardiac coordinate systemProbe orientationFilterHigher spatial resolutionCardiac datasetsEnhanced accuracyMonte-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-makingNetworkTAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction
Guo X, Shi L, Chen X, Liu Q, Zhou B, Xie H, Liu Y, Palyo R, Miller E, Sinusas A, Staib L, Spottiswoode B, Liu C, Dvornek N. TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction. Medical Image Analysis 2024, 96: 103190. PMID: 38820677, PMCID: PMC11180595, DOI: 10.1016/j.media.2024.103190.Peer-Reviewed Original ResearchGenerative adversarial networkAdversarial networkMotion estimation accuracyInter-frame motionIntensity-based image registration techniqueAll-to-oneSegmentation masksImage registration techniquesOriginal frameTemporal informationDiagnosis accuracyMyocardial blood flowEstimation accuracyFrame conversionPositron emission tomographyNovel methodImage qualityPET datasetsRegistration techniqueNetworkCardiac positron emission tomographyBlood flowDynamic cardiac positron emission tomographyMotion correctionCoronary artery diseaseMulti-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography
Ta K, Ahn S, Thorn S, Stendahl J, Zhang X, Langdon J, Staib L, Sinusas A, Duncan J. Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography. IEEE Transactions On Medical Imaging 2024, 43: 2010-2020. PMID: 38231820, DOI: 10.1109/tmi.2024.3355383.Peer-Reviewed Original ResearchMulti-task learning networkCross-stitch unitsComposite loss functionAccurate motion estimationTask-specific networksMotion estimationSegmentation masksLearning networkLoss functionSegmentation stepEchocardiography datasetNetworkMotion displacementMotion analysisMultiple time framesTaskAnalysis pipelineSegmentsStrain measurementsDatasetRepresentationIn vivo neuropil density from anatomical MRI and machine learning
Akif A, Staib L, Herman P, Rothman D, Yu Y, Hyder F. In vivo neuropil density from anatomical MRI and machine learning. Cerebral Cortex 2024, 34: bhae200. PMID: 38771239, PMCID: PMC11107380, DOI: 10.1093/cercor/bhae200.Peer-Reviewed Original ResearchConceptsMagnetic resonance imagingSynaptic densityNeuropil densityCellular densityArtificial neural networkNeural networkPositron emission tomographyAnatomical magnetic resonance imagingHealthy subjectsSynaptic activityMRI scansMachine learning algorithmsBrain's energy budgetEmission tomographyIn vivo MRI scansResonance imagingTissue cellularityLearning algorithmsDiffusion magnetic resonance imagingMachine learningMicroscopic interpretationInterpretation of functional neuroimaging dataIndividual predictionsSubjectsMulticenter Quantification of Radiation Exposure and Associated Risks for Prostatic Artery Embolization in 1476 Patients.
Ayyagari R, Rahman S, Grizzard K, Mustafa A, Staib L, Makkia R, Bhatia S, Bilhim T, Carnevale F, Davis C, Fischman A, Isaacson A, McClure T, McWilliams J, Nutting C, Richardson A, Salem R, Sapoval M, Yu H. Multicenter Quantification of Radiation Exposure and Associated Risks for Prostatic Artery Embolization in 1476 Patients. Radiology 2024, 310: e231877. PMID: 38441098, DOI: 10.1148/radiol.231877.Peer-Reviewed Original ResearchConceptsProstatic artery embolizationCumulative air kermaRadiation-related adverse eventsBody mass indexAdverse eventsEffective doseFluoroscopy timeArtery embolizationRadiation doseKerma area product valuesMedian cumulative air kermaMedian effective radiation doseFluoroscopy unitPatient body mass indexRadiation exposureTwo-sample <i>t</i> test wasRadiation dose dataBenign prostatic hyperplasiaFluoroscopy-guided proceduresPatient radiation exposureEffective radiation doseRadiation field areaRadiation effective doseWilcoxon rank sum testInvasive angiographic proceduresReliable Prostate Cancer Risk Mapping From MRI Using Targeted and Systematic Core Needle Biopsy Histopathology
Zeevi T, Leapman M, Sprenkle P, Venkataraman R, Staib L, Onofrey J. Reliable Prostate Cancer Risk Mapping From MRI Using Targeted and Systematic Core Needle Biopsy Histopathology. IEEE Transactions On Biomedical Engineering 2024, 71: 1084-1091. PMID: 37874731, PMCID: PMC10901528, DOI: 10.1109/tbme.2023.3326799.Peer-Reviewed Original ResearchMagnetic resonance imagingIndividual patientsBiopsy locationProstate biopsy dataBiopsy histopathologyHistopathology scoresPathology scoresBiopsy dataMRI biomarkersTreatment planPatientsResonance imagingProstate regionBiomarkersTherapy treatment plansPathologyRepresentative sampleScoresImaging analysisPrevious studiesHistopathologyProstateCancerCliniciansChapter 13 Data-driven learning strategies for biomarker detection and outcome prediction in Autism from task-based fMRI
Duncan J, Staib L, Dvornek N, Li X, Zhuang J, Wang J, Ventola P. Chapter 13 Data-driven learning strategies for biomarker detection and outcome prediction in Autism from task-based fMRI. 2024, 357-393. DOI: 10.1016/b978-0-32-385124-4.00024-6.Peer-Reviewed Original ResearchLong short-term memoryGraph neural networksFunctional magnetic resonance imagingAutism spectrum disorderNeural ordinary differential equationsData-driven learning strategyDeep learning techniquesTask-based functional magnetic resonance imagingShort-term memoryNeural networkLearning techniquesImpaired social interactionTerm memoryBehavioral therapyRepetitive behaviorsSpectrum disorderDevelopmental disordersLearning strategiesSpatio-temporal characteristicsInherent dynamicsCharacterization of individualsModel of causalitySocial interactionNetworkPersonalized outcome predictions
2023
Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective.
You C, Dai W, Min Y, Liu F, Clifton D, Zhou S, Staib L, Duncan J. Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective. Advances In Neural Information Processing Systems 2023, 36: 9984-10021. PMID: 38813114, PMCID: PMC11136570.Peer-Reviewed Original ResearchMedical image segmentationContrastive learningImage segmentationSemi-supervised medical image segmentationSemi-supervised contrastive learningSelf-supervised objectiveSemantic segmentation datasetsSemi-supervised methodGround-truth labelsQuality of visual representationSafety-critical tasksSegmentation datasetTail classesSegmentation taskLabel setsTruth labelsCL frameworkNegative examplesModel collapseVariance-reductionVariance-reduction techniquesVisual representationTaskLearningPairs of samplesDeferral of Estimated Glomerular Filtration Rate Testing Before Contrast-Enhanced CT in Low-Risk Emergency Department Patients: Assessment of Safety and Impact on Throughput
Gunabushanam G, Asch D, van Luling J, Kuehne A, Alkukhun A, Staib L, Venkatesh A, Pahade J. Deferral of Estimated Glomerular Filtration Rate Testing Before Contrast-Enhanced CT in Low-Risk Emergency Department Patients: Assessment of Safety and Impact on Throughput. Journal Of The American College Of Radiology 2023, 21: 52-60. PMID: 37939813, DOI: 10.1016/j.jacr.2023.11.003.Peer-Reviewed Original ResearchAcute kidney injuryChronic kidney diseaseContrast-enhanced CTLower riskED providersMedian OSEGFR testingContrast-induced acute kidney injuryLow-risk emergency department patientsLow-risk ED patientsProportion of patientsEmergency department patientsClinical risk assessmentGlomerular filtration rate testingAssessment of safetyChronic dialysisKidney injuryDepartment patientsED patientsEGFR valuesKidney diseaseRisk factorsPatientsCECT studiesRiskImplicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
You C, Dai W, Min Y, Staib L, Duncan J. Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts. Lecture Notes In Computer Science 2023, 14222: 561-571. PMID: 38840671, PMCID: PMC11151725, DOI: 10.1007/978-3-031-43898-1_54.Peer-Reviewed Original ResearchMedical image segmentationImage segmentationSegmentation methodPixel-level featuresComputer graphics problemImplicit neural representationsGrid-based representationMedical segmentationRendering frameworkSegmentation predictionsEnd mannerCorrelated contentCompetitive performance improvementsGraphics problemsSegmentationPoint representationPerformance improvementRegular gridSuch informationRepresentationConvolution operatorsExpertsComplex signalsRenderingFeaturesACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast
You C, Dai W, Min Y, Staib L, Sekhon J, Duncan J. ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast. Lecture Notes In Computer Science 2023, 14223: 194-205. PMID: 38813456, PMCID: PMC11136572, DOI: 10.1007/978-3-031-43901-8_19.Peer-Reviewed Original ResearchLearning Sequential Information in Task-Based fMRI for Synthetic Data Augmentation
Wang J, Dvornek N, Staib L, Duncan J. Learning Sequential Information in Task-Based fMRI for Synthetic Data Augmentation. Lecture Notes In Computer Science 2023, 14312: 79-88. PMID: 39281201, PMCID: PMC11395879, DOI: 10.1007/978-3-031-44858-4_8.Peer-Reviewed Original ResearchFunctional magnetic resonance imagesData augmentationClassification taskSpecific cognitive tasksMedical image analysisSynthetic data augmentationEffective data augmentationDownstream learning tasksCognitive tasksVariational autoencoder modelLearning taskTraining dataAutoencoder modelTemporal informationTraining datasetSequential informationSynthetic imagesTaskFMRI sequencesImage analysisMultiple perspectivesMagnetic resonance imagesImagesDifferent alternativesPersistent issueA Multiclass Radiomics Method–Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans
Henao J, Depotter A, Bower D, Bajercius H, Todorova P, Saint-James H, de Mortanges A, Barroso M, He J, Yang J, You C, Staib L, Gange C, Ledda R, Caminiti C, Silva M, Cortopassi I, Dela Cruz C, Hautz W, Bonel H, Sverzellati N, Duncan J, Reyes M, Poellinger A. A Multiclass Radiomics Method–Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans. Investigative Radiology 2023, 58: 882-893. PMID: 37493348, PMCID: PMC10662611, DOI: 10.1097/rli.0000000000001005.Peer-Reviewed Original ResearchConceptsCOVID-19 positive patientsClinical Progression ScaleLung lesionsLesion modelDisease severityGround-glass opacitiesCOVID-19 patientsRadiologist assessmentExpert thoracic radiologistsMulticenter cohortPleural effusionDisease extentRetrospective studyDevelopment cohortPatient assessmentTomography scanCT scanSeverity ScalePatient's diseaseTissue lesionsThoracic radiologistsLesionsPatientsRadiomics modelRadiomic featuresBootstrapping Semi-supervised Medical Image Segmentation with Anatomical-Aware Contrastive Distillation
You C, Dai W, Min Y, Staib L, Duncan J. Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-Aware Contrastive Distillation. Lecture Notes In Computer Science 2023, 13939: 641-653. PMID: 37409056, PMCID: PMC10322187, DOI: 10.1007/978-3-031-34048-2_49.Peer-Reviewed Original ResearchPredicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning
Kucukkaya A, Zeevi T, Chai N, Raju R, Haider S, Elbanan M, Petukhova-Greenstein A, Lin M, Onofrey J, Nowak M, Cooper K, Thomas E, Santana J, Gebauer B, Mulligan D, Staib L, Batra R, Chapiro J. Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning. Scientific Reports 2023, 13: 7579. PMID: 37165035, PMCID: PMC10172370, DOI: 10.1038/s41598-023-34439-7.Peer-Reviewed Original ResearchIntegrating Prostate Specific Antigen Density Biomarker Into Deep Learning Prostate MRI Lesion Segmentation Models
Zhong J, Staib L, Venkataraman R, Onofrey J. Integrating Prostate Specific Antigen Density Biomarker Into Deep Learning Prostate MRI Lesion Segmentation Models. 2011 IEEE International Symposium On Biomedical Imaging: From Nano To Macro 2023, 00: 1-5. PMID: 38090633, PMCID: PMC10711801, DOI: 10.1109/isbi53787.2023.10230418.Peer-Reviewed Original Research