Nicha Dvornek, PhD
Assistant Professor of Radiology and Biomedical ImagingDownloadHi-Res Photo
Cards
Appointments
Contact Info
About
Titles
Assistant Professor of Radiology and Biomedical Imaging
Appointments
Radiology & Biomedical Imaging
Assistant ProfessorPrimary
Other Departments & Organizations
Education & Training
- Postdoctoral Fellow
- Yale School of Medicine (2017)
- Postdoctoral Associate
- Yale School of Medicine (2015)
- PhD
- Yale University (2012)
- MPhil
- Yale University (2009)
- MS
- Yale University (2007)
- BS
- Johns Hopkins University (2006)
Research
Overview
Medical Research Interests
Autistic Disorder; Biomedical Engineering; Brain; Image Processing, Computer-Assisted; Neural Networks, Computer
ORCID
0000-0002-1648-6055
Research at a Glance
Publications Timeline
A big-picture view of Nicha Dvornek's research output by year.
Yale Co-Authors
Frequent collaborators of Nicha Dvornek's published research.
Research Interests
Research topics Nicha Dvornek is interested in exploring.
49Publications
1,584Citations
James Duncan, PhD
Lawrence Staib, PhD
Chi Liu, PhD
John Onofrey, PhD
Edward J Miller, MD, PhD
Albert Sinusas, MD
Brain
Image Processing, Computer-Assisted
Neural Networks, Computer
Publications
Featured Publications
Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network
Guo X, Zhou B, Pigg D, Spottiswoode B, Casey ME, Liu C, Dvornek NC. Unsupervised inter-frame motion correction for whole-body dynamic PET using convolutional long short-term memory in a convolutional neural network. Medical Image Analysis 2022, 80: 102524. PMID: 35797734, PMCID: PMC10923189, DOI: 10.1016/j.media.2022.102524.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsConvolutional neural networkNeural networkConvolutional long short-term memory (ConvLSTM) layersDeep learning-based frameworkConvolutional long short-term memoryLong short-term memory layersDeep learning baselinesLong short-term memoryDynamic temporal featuresLearning-based frameworkDeep learning approachShort-term memory layersTracer distribution changeMotion estimation networkMotion prediction errorInference timeEstimation networkLearning baselinesNon-rigid registration methodLearning approachMotion correction methodMemory layerShort-term memoryTemporal featuresRegistration method
2025
Geometry-Guided Local Alignment for Multi-view Visual Language Pre-training in Mammography
Du Y, Chen L, Dvornek N. Geometry-Guided Local Alignment for Multi-view Visual Language Pre-training in Mammography. Lecture Notes In Computer Science 2025, 15965: 299-310. DOI: 10.1007/978-3-032-04978-0_29.Peer-Reviewed Original ResearchConceptsVisual language modelMulti-view image processingLanguage pre-trainingMulti-view relationshipsDeep learning methodsDomain-specific characteristicsContrastive learningNatural imagesCorrespondence learningLanguage modelLocal featuresMammography datasetGeometry guidanceLocal alignmentPre-trainingLearning methodsMedical imagesDomain differencesMultiple datasetsIndependent imagesProcessing of mammogramsSuboptimal predictionsDatasetLearningEarly detection of breast cancerMulti-view and Multi-scale Alignment for Contrastive Language-Image Pre-training in Mammography
Du Y, Onofrey J, Dvornek N. Multi-view and Multi-scale Alignment for Contrastive Language-Image Pre-training in Mammography. Lecture Notes In Computer Science 2025, 15830: 247-262. PMID: 40995617, PMCID: PMC12456755, DOI: 10.1007/978-3-031-96625-5_17.Peer-Reviewed Original ResearchCitationsConceptsContrastive Language-Image Pre-trainingMulti-viewPre-trainingState-of-the-art baselinesMulti-view natureState-of-the-artMedical image analysisHigh-resolution imagesFine-tuning approachLanguage modelMammography datasetComputational resourcesModel sizeSupervised frameworkMulti-scaleData scarcityImage focusImage analysisMedical knowledgeImagesDatasetUnder-exploredSmall regionCXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray
Lin M, Holste G, Wang S, Zhou Y, Wei Y, Banerjee I, Chen P, Dai T, Du Y, Dvornek N, Ge Y, Guo Z, Hanaoka S, Kim D, Messina P, Lu Y, Parra D, Son D, Soto Á, Urooj A, Vidal R, Yamagishi Y, Yan P, Yang Z, Zhang R, Zhou Y, Celi L, Summers R, Lu Z, Chen H, Flanders A, Shih G, Wang Z, Peng Y. CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray. Medical Image Analysis 2025, 106: 103739. PMID: 40795541, PMCID: PMC12396843, DOI: 10.1016/j.media.2025.103739.Peer-Reviewed Original ResearchCitationsMeSH Keywords and ConceptsConceptsLung disease classificationState-of-the-art solutionsState-of-the-art techniquesZero-shot generalizationZero-shot learningNoisy test setsLong-tailed classificationState-of-the-artChest X-ray dataDisease classificationData curation processesDisease classification performanceNoisy labelsMulti-labelClassification performanceGeneration approachMICCAI challengeTest setDisease labelsCuration processDisease detectionMultimodal modelClassificationLearning strategiesDatasetCausal Modeling of FMRI Time-Series for Interpretable Autism Spectrum Disorder Classification
Duan P, Dvornek N, Wang J, Staib L, Duncan J. Causal Modeling of FMRI Time-Series for Interpretable Autism Spectrum Disorder Classification. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10980933.Peer-Reviewed Original ResearchConceptsFunctional magnetic resonance imagingAutism spectrum disorderState-of-the-art modelsState-of-the-artFMRI time seriesDeep learning classifierDeep learning modelsTime series informationLearning classifiersClassification accuracyNon-linear interactionsMachine learningLeft precuneusRight precuneusABIDE datasetBrain regionsLearning modelsASD populationSpectrum disorderDisorder classificationASD classificationBrain signalsASD biomarkersDevelopmental disordersCorrelation-based modelsTowards Zero-Shot Task-Generalizable Learning on FMRI
Wang J, Dvornek N, Duan P, Staib L, Duncan J. Towards Zero-Shot Task-Generalizable Learning on FMRI. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10981094.Peer-Reviewed Original ResearchConceptsContextual informationLearn contextual informationNeural network architectureTask-based fMRIPlug-and-playDownstream tasksNetwork architectureTask-dependent signalsTask-based paradigmsFunctional brain patternsResting-state fMRIMultiple modulesTaskFMRI taskBrain activityArchitectureBOLD signalResting-stateFMRIBrain functionBrain patternsTask designResting stateInformationEncodingImproved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net
Zhang J, Du Y, Dvornek N, Onofrey J. Improved Vessel Segmentation with Symmetric Rotation-Equivariant U-Net. 2025, 00: 1-5. DOI: 10.1109/isbi60581.2025.10981208.Peer-Reviewed Original ResearchConceptsConvolutional neural networkU-NetModel sizeSmall memory costMedical image analysisU-Net architectureImproved vessel segmentationTrainable parametersMemory costComputer-Assisted InterventionSegmentation performanceNeural networkLearning methodsVessel segmentationLearning costLearning approachEquivariance propertyFundus imagesInconsistent predictionsAutomated SegmentationImage analysisPerformanceSegmentsImagesArchitectureSRE-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 ResearchConceptsConvolutional 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 performanceConnectome-based predictive modeling of early and chronic psychosis symptoms
Foster M, Ye J, Powers A, Dvornek N, Scheinost D. Connectome-based predictive modeling of early and chronic psychosis symptoms. Neuropsychopharmacology 2025, 50: 877-885. PMID: 40016363, PMCID: PMC12032145, DOI: 10.1038/s41386-025-02064-9.Peer-Reviewed Original ResearchCitationsAltmetricConceptsConnectome-based predictive modelingPositive and Negative Syndrome ScalePsychosis symptomsSymptom networksSymptom severityBrain networksNeural correlates of CPResting-state functional magnetic resonance imagingFunctional magnetic resonance imagingNegative Syndrome ScaleIdentified group differencesPredicted effect sizeCorrelates of CPGeneral psychopathologyNegative symptomsPositive symptomsSyndrome ScaleFrontoparietal networkNeural correlatesVirtual lesion analysisGroup differencesConnectivity changesEffect sizeLesion analysisLongitudinal study
2024
Style mixup enhanced disentanglement learning for unsupervised domain adaptation in medical image segmentation
Cai Z, Xin J, You C, Shi P, Dong S, Dvornek N, Zheng N, Duncan J. Style mixup enhanced disentanglement learning for unsupervised domain adaptation in medical image segmentation. Medical Image Analysis 2024, 101: 103440. PMID: 39764933, DOI: 10.1016/j.media.2024.103440.Peer-Reviewed Original ResearchCitationsAltmetricMeSH Keywords and ConceptsConceptsUnsupervised domain adaptationMedical image segmentationDomain-invariant representationsImage segmentationDomain adaptationDisentanglement learningImage translationUnsupervised domain adaptation approachState-of-the-art methodsDomain shift problemDomain-invariant learningState-of-the-artPublic cardiac datasetsDiverse constraintsAdversarial learningConsistency regularizationContrastive learningFeature spaceSemantic consistencyComprehensive experimentsDomain generalizationData diversityShift problemMedical segmentationCardiac datasets
Clinical Trials
Current Trials
ACE Multisite Study of Adolescent & Adult Transitions
HIC ID2000024998RoleSub InvestigatorPrimary Completion Date04/30/2024Recruiting ParticipantsGenderBothAge12 years - 35 yearsCBT for Anxiety in Children With Autism
HIC ID1211011144RoleSub InvestigatorPrimary Completion Date06/30/2020Recruiting ParticipantsGenderBothAge8 years - 14 years
Academic Achievements & Community Involvement
Honors
honor Best Paper Award
10/13/2019International Award10th International Workshop on Machine Learning in Medical Imaging (MLMI 2019)DetailsChinahonor Best Challenger Award
10/13/2019International AwardConnectomics in Neuroimaging - Transfer Learning ChallengeDetailsChinahonor James Hudson Brown – Alexander Brown Coxe Postdoctoral Fellowship
07/01/2014Yale School of Medicine AwardYale School of MedicineDetailsUnited States
News
News
- April 08, 2025
Understanding the Transition From Early to Chronic Psychosis
- September 13, 2022
NIH Autism Center of Excellence Program Includes Yale Researchers
Get In Touch
Contacts
Locations
N309A
Academic Office
The Anlyan Center
300 Cedar Street
New Haven, CT 06519