Tal Zeevi
Postgraduate AssociateAbout
Research
Publications
2025
CT Radiomic Features are Associated with DNA Copy Number Alterations of Head and Neck Squamous Cell Carcinomas.
Haider S, Schreier A, Zeevi T, Gross M, Paul B, Krenn J, Canis M, Baumeister P, Reichel C, Payabvash S, Sharaf K. CT Radiomic Features are Associated with DNA Copy Number Alterations of Head and Neck Squamous Cell Carcinomas. American Journal Of Neuroradiology 2025, ajnr.a9029. PMID: 41067910, DOI: 10.3174/ajnr.a9029.Peer-Reviewed Original ResearchHead and neck squamous cell carcinomaNeck squamous cell carcinomaSquamous cell carcinomaCna-positiveRadiomic phenotypesCell carcinomaFraction of head and neck squamous cell carcinomasHNSCC primary tumorsHierarchical clustering of patientsRadiomic featuresCT radiomics featuresRadiomics-based prediction modelCopy number alterationsBiological significanceCopy number dataClusters of patientsUnivariate association analysisOncological outcomesNeck CTPrimary tumorContrast CT imagesUnivariate analysisMultiple testing correctionRadiomics analysisSomatic mutationsImpact of Childhood Neighborhood Deprivation on White Matter and Functional Connectivity During Adolescence
Acosta‐Rodriguez H, Bobba P, Stephan A, Zeevi T, Malhotra A, Tran A, Kaltenhauser S, Ment L, Payabvash S. Impact of Childhood Neighborhood Deprivation on White Matter and Functional Connectivity During Adolescence. Journal Of Neuroimaging 2025, 35: e70087. PMID: 40916058, DOI: 10.1111/jon.70087.Peer-Reviewed Original ResearchConceptsArea Deprivation IndexNeighborhood deprivationSocioeconomic determinantsNeighborhood socioeconomic disadvantageAdult health outcomesPoor neighborhoodsBody mass indexDeprivation indexSocioeconomic disadvantageAdolescent Brain Cognitive Development StudyHealth outcomesDeprived neighbourhoodsFollow-upRepresentative cohortDemographically representative cohortCognitive Development StudyMass indexParental educationWM microstructural integrityChildhood developmentChildhood neighborhoodIncome levelPreadolescent brainSample sizePhysical environmentNeuroimaging markers of cognition in late childhood associated with moderate to late preterm birth
Acosta-Rodriguez H, Bobba P, Zeevi T, Ment L, Payabvash S. Neuroimaging markers of cognition in late childhood associated with moderate to late preterm birth. Pediatric Research 2025, 1-10. PMID: 40753115, DOI: 10.1038/s41390-025-04286-5.Peer-Reviewed Original ResearchModerate to late pretermGestational agePreterm birthPoor cognitive outcomesModerate to late preterm birthNeurodevelopmental alterationsProportion of preterm birthsLow gestational ageLate preterm birthFrontal lobeFull-term childrenNeuroimaging markersCognitive outcomesNeurocognitive performanceNeurocognitive testsLate pretermPreterm childrenFull-termWhite matter integrityPretermExecutive functionBrain alterationsBirthConclusionThese findingsMorphological alterationsNoninvasive Tumor Profiling: Quantitative Contrast-Enhanced MRI Markers Predict PD-L1 and CTNNB1 Status in Hepatocellular Carcinoma.
Matuschewski N, Sobirey R, Revzin M, Zeevi T, Gross M, Kasolowsky V, Shewarega A, Meister E, Kao T, Tefera J, Bousabarah K, Batra R, Strazzabosco M, Lin M, Gebauer B, Savic L, Duncan J, Madoff D, Zhang X, Chapiro J. Noninvasive Tumor Profiling: Quantitative Contrast-Enhanced MRI Markers Predict PD-L1 and CTNNB1 Status in Hepatocellular Carcinoma. Radiology 2025, 316: e242750. PMID: 40762840, PMCID: PMC12405729, DOI: 10.1148/radiol.242750.Peer-Reviewed Original ResearchRate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
Zeevi T, Shwartz-Ziv R, LeCun Y, Staib L, Onofrey J. Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation. 2025, 00: 20757-20766. DOI: 10.1109/cvpr52734.2025.01933.Peer-Reviewed Original ResearchLayer feature mapsMedical imaging tasksFeature mapsInformation lossImaging tasksMonte Carlo dropoutPredictive uncertainty estimationInformation-theoretic principlesInference-timeUncertainty estimationPerceptual qualityNetwork layerAccurate uncertainty estimatesData distributionNeural networkNoise injectionSynthetic dataStochastic forwardArchitectural configurationsMedical diagnosisIndividual inputsPredictive performanceNetworkPrediction uncertaintyTaskFDG-PET Intensity Normalization Improves Radiomics-Based Survival Prediction in Patients with Oropharyngeal Cancer: A Comparison of the Standardized Uptake Value with Alternative Normalization Techniques.
Payabvash S, Sharaf K, Zeevi T, Gross M, Mahajan A, Kann B, Judson B, Schreier A, Krenn J, Prasad M, Burtness B, Aboian M, Canis M, Baumeister P, Reichel C, Haider S. FDG-PET Intensity Normalization Improves Radiomics-Based Survival Prediction in Patients with Oropharyngeal Cancer: A Comparison of the Standardized Uptake Value with Alternative Normalization Techniques. American Journal Of Neuroradiology 2025, 46: 2370-2376. PMID: 40379456, PMCID: PMC12629553, DOI: 10.3174/ajnr.a8836.Peer-Reviewed Original ResearchOropharyngeal squamous cell carcinomaStandardized uptake valueSquamous cell carcinomaFDG-PETRadiomic featuresPET featuresOncological outcomesLentiform nucleusCell carcinomaUptake valuePrognostic value of radiomics featuresC-indexOropharyngeal squamous cell carcinoma patientsValue of radiomic featuresProgression-free survivalOropharyngeal cancer patientsUnivariate Cox regression modelPredicting oncological outcomesRandom survival forestArea under the curveHarrell's concordance indexIndividual radiomics featuresStandardized uptake ratioHarrell's C-indexCox regression modelsImage-Based Search in Radiology: Identification of Brain Tumor Subtypes within Databases Using MRI-Based Radiomic Features.
von Reppert M, Chadha S, Willms K, Avesta A, Maleki N, Zeevi T, Lost J, Tillmanns N, Jekel L, Merkaj S, Lin M, Hoffmann K, Aneja S, Aboian M. Image-Based Search in Radiology: Identification of Brain Tumor Subtypes within Databases Using MRI-Based Radiomic Features. American Journal Of Neuroradiology 2025, 46: 1421-1428. PMID: 40250848, PMCID: PMC12453443, DOI: 10.3174/ajnr.a8805.Peer-Reviewed Original ResearchConceptsDimensionality reduction techniquesQuery caseImage search enginesImage-based searchReduction techniquesQuery subsetsRetrieval performanceQuery onesDimensionality reductionVisual similarityQuerySearch enginesSearch approachSearch methodTumor segmentationImage-basedRadiomic featuresNearest neighborsTumor typesDimensionalityBrain tumorsData setsNinety-five patientsLikert scoresMRI-based radiomic featuresSRE-CONV: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification
Du Y, Zhang J, Zeevi T, Dvornek N, Onofrey J. SRE-CONV: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10981270.Peer-Reviewed Original ResearchConvolutional neural networkConvolutional neural network backboneComputer vision tasksBiomedical image classificationRotation-invariant featuresReduced memory footprintVision tasksEquivariant convolutionImage classificationIncreased training costsMemory footprintRotation-equivariantData augmentationNeural networkModel sizeTraining costsTest datasetInfor-mationPerformance accuracyParam-etersBiomedical imagingDatasetIncor-poratedEquivarianceModel performanceEnhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout
Zeevi T, Staib L, Onofrey J. Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropout. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10980684.Peer-Reviewed Original ResearchSemantic segmentationDeterministic neural networksChest X-ray scansFeature mapsTraditional dropoutSegmentation taskMC dropoutNeural networkMedical imagesSignal spaceSemantic uncertaintyContrast-enhanced CTEnhance medical decision-makingBiparametric MRIPractical solutionProstate zonesFrequency domainLiver tumorsMonte-CarloX-ray scansUncertainty estimationBoundary delineationMC frequencyTextural variationsImaging modalitiesStrategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging
Tran A, Zeevi T, Payabvash S. Strategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging. BioMedInformatics 2025, 5: 20. PMID: 40271381, PMCID: PMC12014193, DOI: 10.3390/biomedinformatics5020020.Peer-Reviewed Original ResearchDeep learning modelsGeneralizability of deep learning modelsLearning modelsArtificial intelligenceIntegration of deep learning modelsImprove model robustnessDomain shiftEnhance deep learningTransfer learningData augmentationDeep learningMedical imagesTask-specific applicationsModel robustnessSensitive to artifactsLearning segmentationDeep learning segmentationModel attributesNeuroimaging applicationsRobustnessClassificationDataUncertainty estimationLearningData variability
Links
Get In Touch
Contacts
Email