Featured Publications
Reliable 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 studiesHistopathologyProstateCancerCliniciansAutomated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning
Gross M, Haider S, Ze’evi T, Huber S, Arora S, Kucukkaya A, Iseke S, Gebauer B, Fleckenstein F, Dewey M, Jaffe A, Strazzabosco M, Chapiro J, Onofrey J. Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning. European Radiology 2024, 34: 6940-6952. PMID: 38536464, PMCID: PMC11399284, DOI: 10.1007/s00330-024-10624-8.Peer-Reviewed Original ResearchContrast-enhanced magnetic resonance imagingMagnetic resonance imagingClinical staging systemTime of diagnosisHepatocellular carcinomaClinical dataMortality risk predictionOverall survivalStaging systemRadiomic featuresManagement of hepatocellular carcinomaPersonalized follow-up strategiesAssociated with OSMethodsThis retrospective studyHepatocellular carcinoma patientsBaseline magnetic resonance imagingMRI radiomics featuresIndependent validation cohortHarrell's C-indexRisk predictionFollow-up strategiesHigh-risk groupPredictive risk scoreRadiomics feature extractionMedian timeAutomated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics
Gross M, Huber S, Arora S, Ze’evi T, Haider S, Kucukkaya A, Iseke S, Kuhn T, Gebauer B, Michallek F, Dewey M, Vilgrain V, Sartoris R, Ronot M, Jaffe A, Strazzabosco M, Chapiro J, Onofrey J. Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics. European Radiology 2024, 34: 5056-5065. PMID: 38217704, PMCID: PMC11245591, DOI: 10.1007/s00330-023-10495-5.Peer-Reviewed Original ResearchMagnetic resonance imagingRadiomics feature extractionLiver volumetryIntraclass correlation coefficientRadiomic featuresLiver segmentationAutomated liver volumetryHepatocellular carcinoma patientsMann-Whitney U testAutomated liver segmentationManual segmentationQuantitative imaging biomarkersCarcinoma patientsRetrospective studyInstitutional databaseAnatomical localizationClinical relevanceManual volumetryMann-WhitneyU testExternal validationInternal test setImaging biomarkersInclusion criteriaResultsIn totalIntegrating 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 ResearchFast Reconstruction for Deep Learning PET Head Motion Correction
Zeng T, Zhang J, Lieffrig E, Cai Z, Chen F, You C, Naganawa M, Lu Y, Onofrey J. Fast Reconstruction for Deep Learning PET Head Motion Correction. Lecture Notes In Computer Science 2023, 14229: 710-719. PMID: 38174207, PMCID: PMC10758999, DOI: 10.1007/978-3-031-43999-5_67.Peer-Reviewed Original ResearchCross-Attention for Improved Motion Correction in Brain PET
Cai Z, Zeng T, Lieffrig E, Zhang J, Chen F, Toyonaga T, You C, Xin J, Zheng N, Lu Y, Duncan J, Onofrey J. Cross-Attention for Improved Motion Correction in Brain PET. Lecture Notes In Computer Science 2023, 14312: 34-45. PMID: 38174216, PMCID: PMC10758996, DOI: 10.1007/978-3-031-44858-4_4.Peer-Reviewed Original ResearchDeep learning networkCross-attention mechanismDeep learning benchmarksMotion correctionTraining data domainPET list-mode dataPET image reconstructionQuality of reconstructionData domainCross attentionLearning networkSupervised mannerLearning benchmarksReference imageMotion trackingInherent informationList-mode dataImage reconstructionBrain PET dataPrediction resultsDifferent scannersHead motionImproved motion correctionNetworkSpatial correspondence
2024
AI-driven Patient-Selection For Preoperative Portal Vein Embolization For Patients With Colorectal Cancer Liver Metastases
Kuhn T, Engelhardt W, Kahl V, Alkukhun A, Gross M, Iseke S, Onofrey J, Covey A, Camacho Vasquez J, Kawaguchi Y, Hasegawa K, Odisio B, Vauthey J, Antoch G, Chapiro J, Madoff D. AI-driven Patient-Selection For Preoperative Portal Vein Embolization For Patients With Colorectal Cancer Liver Metastases. Journal Of Vascular And Interventional Radiology 2024 PMID: 39638087, DOI: 10.1016/j.jvir.2024.11.025.Peer-Reviewed Original ResearchTotal liver volumeMetastatic colorectal cancer patientsPreoperative portal vein embolizationColorectal cancer liver metastasesPortal vein embolizationCancer liver metastasesMulticenter retrospective studyColorectal cancer patientsStudent's t-testBoard-certified radiologistsVein embolizationConsecutive patientsLiver metastasesLiver volumePatient selectionRetrospective studyCancer patientsRadiomic featuresInclusion criteriaPatientsSemi-automatic segmentationLab valuesT-testSDAUCCT-Less Whole-Body Bone Segmentation of PET Images Using a Multimodal Deep Learning Network
Bao N, Zhang J, Li Z, Wei S, Zhang J, Greenwald S, Onofrey J, Lu Y, Xu L. CT-Less Whole-Body Bone Segmentation of PET Images Using a Multimodal Deep Learning Network. IEEE Journal Of Biomedical And Health Informatics 2024, PP: 1-16. DOI: 10.1109/jbhi.2024.3501386.Peer-Reviewed Original ResearchPositron emission tomographyMultimodal fusion modulePositron emission tomography imagingMultimodal fusion networkAttenuation mapDice similarity coefficientFusion moduleFusion networkEncoder RepresentationsEncoder branchesCT imagesTraining dataComputed tomographyTumor analysisTracer activityModality imagesMultimodal deep learning networkPET imagingBone segmentsSqueeze-and-excitationBone cancerPositron emission tomography informationCT-based approachDeep learning networkImprove segmentation performanceBias in medical AI: Implications for clinical decision-making
Cross J, Choma M, Onofrey J. Bias in medical AI: Implications for clinical decision-making. PLOS Digital Health 2024, 3: e0000651. PMID: 39509461, PMCID: PMC11542778, DOI: 10.1371/journal.pdig.0000651.Peer-Reviewed Original ResearchMedical AIArtificial intelligenceClinical decision-makingSupervised learning modelsMedical artificial intelligenceDiverse data setsSocial determinants of healthDeployment solutionDeterminants of healthAI algorithmsData featuresDebiasing methodsPerformance metricsLearning modelsAI lifecycleAI developmentModel interpretationData setsSuboptimal performanceModel's clinical utilityHealthcare disparitiesSocial determinantsCare practicesDecision-makingImplicit cognitive biasesData-driven non-rigid motion detection and correction for NeuroEXPLORER
Zhang J, Sun C, Volpi T, Zeng T, Fontaine K, Du Y, Toyonaga T, Onofrey J, Lu Y, Carson R. Data-driven non-rigid motion detection and correction for NeuroEXPLORER. 2024, 00: 1-2. DOI: 10.1109/nss/mic/rtsd57108.2024.10658289.Peer-Reviewed Original ResearchNon-rigid motionNon-rigid motion estimationMotion dataNon-rigid regionsHead motion dataTracking capabilityMotion estimationMotion detectionRigid transformationImage-derived input functionMotion tracking systemImage blurringCarotid arteryEffective MCMotion patternsPatient movementTracking systemMotion correction frameworkBrain PET systemRigid motionMotion-corrected reconstructionFacial surfaceRigid motion correctionCorrect reconstructionCorrection frameworkAging-dependent loss of functional connectivity in a mouse model of Alzheimer’s disease and reversal by mGluR5 modulator
Mandino F, Shen X, Desrosiers-Grégoire G, O’Connor D, Mukherjee B, Owens A, Qu A, Onofrey J, Papademetris X, Chakravarty M, Strittmatter S, Lake E. Aging-dependent loss of functional connectivity in a mouse model of Alzheimer’s disease and reversal by mGluR5 modulator. Molecular Psychiatry 2024, 1-16. PMID: 39424929, DOI: 10.1038/s41380-024-02779-z.Peer-Reviewed Original ResearchFunctional connectivity deficitsConnectivity deficitsFunctional connectivityBrain connectivityAllosteric modulators of mGluR5Alzheimer's diseaseDefault-mode networkModulation of mGluR5Loss of functional connectivityResting-state fMRIApplication of fMRIWild-type controlsAged AD miceMouse model of Alzheimer's diseaseAD-related changesAD miceModel of Alzheimer's diseaseAssociated with synaptic damageMGluR5 modulationMonths of ageFMRI measurementsAmyloid accumulationDecreased connectivityBrain networksSilent allosteric modulatorsA Flow-based Truncated Denoising Diffusion Model for super-resolution Magnetic Resonance Spectroscopic Imaging
Dong S, Cai Z, Hangel G, Bogner W, Widhalm G, Huang Y, Liang Q, You C, Kumaragamage C, Fulbright R, Mahajan A, Karbasi A, Onofrey J, de Graaf R, Duncan J. A Flow-based Truncated Denoising Diffusion Model for super-resolution Magnetic Resonance Spectroscopic Imaging. Medical Image Analysis 2024, 99: 103358. PMID: 39353335, DOI: 10.1016/j.media.2024.103358.Peer-Reviewed Original ResearchDenoising diffusion modelsDeep learning-based super-resolution methodsLearning-based super-resolution methodsMulti-scale super-resolutionGenerative modelSuper-resolution methodsDeep learning modelsHigh-resolution magnetic resonance spectroscopic imagingHigh-quality imagesPost-processing approachSuper-resolutionFlow-based networksLearning modelsLow resolutionTruncation stepLow-resolution dataSharpness adjustmentNetworkSensitivity restrictionsUncertainty estimationDiffusion modelImagesCapabilitySampling processSpectroscopic imagingMonte-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-makingNetworkBiphasic training for awake imaging using a dual-imaging system reveals neurovascular uncoupling and anesthesia effects in healthy mice
Mandino F, Shen X, Desrosiers-Gregoire G, O'Connor D, Mukherjee B, Ha Y, Qu A, Onofrey J, Papademetris X, Chakravarty M, Strittmatter S, Lake E. Biphasic training for awake imaging using a dual-imaging system reveals neurovascular uncoupling and anesthesia effects in healthy mice. Proceedings Of The International Society For Magnetic Resonance In Medicine ... Scientific Meeting And Exhibition. 2024 DOI: 10.58530/2024/0531.Peer-Reviewed Original ResearchSymmetric Consistency with Cross-Domain Mixup for Cross-Modality Cardiac Segmentation
Cai Z, Xin J, Dong S, Onofrey J, Zheng N, Duncan J. Symmetric Consistency with Cross-Domain Mixup for Cross-Modality Cardiac Segmentation. 2024, 00: 1536-1540. DOI: 10.1109/icassp48485.2024.10447304.Peer-Reviewed Original ResearchPatient-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
Unsupervised Domain Adaptation by Cross-Prototype Contrastive Learning for Medical Image Segmentation
Cai Z, Xin J, Dong S, You C, Shi P, Zeng T, Zhang J, Onofrey J, Zheng N, Duncan J. Unsupervised Domain Adaptation by Cross-Prototype Contrastive Learning for Medical Image Segmentation. 2023, 00: 819-824. DOI: 10.1109/bibm58861.2023.10386055.Peer-Reviewed Original ResearchUnsupervised domain adaptationDistribution alignmentDomain adaptationContrastive learningUnsupervised domain adaptation methodsMedical image segmentation tasksDomain distribution alignmentGlobal distribution alignmentContrastive learning methodDomain adaptation performanceIntra-class distancePixel-level featuresImage segmentation tasksInter-class distancePublic cardiac datasetsCategory centroidDiscrimination of classesClass prototypesSegmentation taskSource domainTarget domainCardiac datasetsLearning methodsGlobal prototypesCentroid alignmentFast Reconstruction Enhances Deep Learning PET Head Motion Correction
Zeng T, Chen F, Zhang J, Lieffrig E, Cai Z, Naganawa M, You C, Lu Y, Onofrey J. Fast Reconstruction Enhances Deep Learning PET Head Motion Correction. 2023, 00: 1-1. DOI: 10.1109/nssmicrtsd49126.2023.10338189.Peer-Reviewed Original ResearchTeacher’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 resultsPerformanceImage Intensity Normalization Benefits Deep Learning Brain PET Motion Correction
Lieffrig E, Zhang J, Zeng T, Cai Z, You C, Lu Y, Onofrey J. Image Intensity Normalization Benefits Deep Learning Brain PET Motion Correction. 2023, 00: 1-1. DOI: 10.1109/nssmicrtsd49126.2023.10338194.Peer-Reviewed Original ResearchInput data normalizationImage intensity normalizationNeural network inputsMedical imaging researchPET motion correctionPre-processing stepMotion prediction errorMotion correctionIntensity normalizationNetwork inputsMotion predictionHead motion correctionInput dataTesting subjectsData normalizationEarly framesSuch methodsPrediction errorImaging researchDifferent normalization strategiesNormalization strategyMachineAlgorithmTaskValue analysis