Tianyi Zeng, PhD
Associate Research ScientistAbout
Research
Publications
2025
Exceptional brain PET images from the NeuroEXPLORER: scans with targeted radiopharmaceuticals and comparison to HRRT
Volpi T, Toyonaga T, Khattar N, Gallezot J, Naganawa M, Vanderlinden G, Honhar P, Zeng T, Fontaine K, Mulnix T, Hu L, Sun X, Henry S, Matuskey D, Radhakrishnan R, Guo L, Hu Y, Zhang J, Zheng X, Nabulsi N, Huang Y, Badawi R, Cherry S, Hillmer A, Jones T, Liu C, Morris E, Qi J, Li H, Carson R. Exceptional brain PET images from the NeuroEXPLORER: scans with targeted radiopharmaceuticals and comparison to HRRT. European Journal Of Nuclear Medicine And Molecular Imaging 2025, 1-12. PMID: 41177836, DOI: 10.1007/s00259-025-07605-4.Peer-Reviewed Original ResearchStandardized uptake valueTargeted radiopharmaceuticalsDopamine systemMultiple cortical areasSerotonin transporterRaphe nucleusMeasurement of tracer uptakeBrain regionsBrain structuresSubcortical nucleiPositron emission tomographyCortical areasSynaptic densityPET researchFocal uptakePaired scansUptake valueTracer uptakePET systemGray matterEarly imagesEmission tomographyHealthy individualsTracer deliveryNeuroExplorerPET Head Motion Estimation Using Supervised Deep Learning with Attention
Cai Z, Zeng T, Zhang J, Lieffrig E, Fontaine K, You C, Revilla E, Duncan J, Xin J, Lu Y, Onofrey J. PET Head Motion Estimation Using Supervised Deep Learning with Attention. IEEE Transactions On Medical Imaging 2025, PP: 1-1. PMID: 41082441, DOI: 10.1109/tmi.2025.3620714.Peer-Reviewed Original ResearchHead motion estimationMotion estimationState-of-the-artMotion estimation methodSupervised deep learningRigid head motionMotion correctionCross-attentionDelineation of brain structuresSupervised mannerDeep learningPositron emission tomography scannerMotion correction approachPET raw dataMotion trackingMotion-free imagesDiagnosis of neurological disordersQuantification inaccuraciesRaw dataHead motionBrain positron emission tomographyEstimation methodHead movementsMotion artifactsQualitative results
2024
High‐resolution motion compensation for brain PET imaging using real‐time electromagnetic motion tracking
Tan W, Wang Z, Zeng X, Boccia A, Wang X, Li Y, Li Y, Fung E, Qi J, Zeng T, Gupta A, Goldan A. High‐resolution motion compensation for brain PET imaging using real‐time electromagnetic motion tracking. Medical Physics 2024, 52: 201-218. PMID: 39422495, PMCID: PMC11716701, DOI: 10.1002/mp.17437.Peer-Reviewed Original ResearchConceptsDepth of interactionMotion correctionPET-CT scannerField of viewEvent-by-event motion correctionPET list-mode dataScanner field of viewList-mode dataMotion-induced blurringPET imagingDipole fieldBrain PET imagingBrain positron emission tomographyFull-widthParallax effectMotion compensationBrain scannerDiameter spheresPhantomFlux densityRecovery coefficientImaging performanceFWHMScanner coordinate systemSpatial resolutionClass-Aware Mutual Mixup with Triple Alignments for Semi-supervised Cross-Domain Segmentation
Cai Z, Xin J, Zeng T, Dong S, Zheng N, Duncan J. Class-Aware Mutual Mixup with Triple Alignments for Semi-supervised Cross-Domain Segmentation. Lecture Notes In Computer Science 2024, 15008: 68-79. DOI: 10.1007/978-3-031-72111-3_7.Peer-Reviewed Original ResearchSemi-supervised domain adaptationCross-domain segmentationTail classesBridge the domain gapState-of-the-art methodsMean-teacher modelUnlabeled target samplesLabeled source samplesState-of-the-artDomain gapDomain adaptationKnowledge distillationMixup strategyIntra-domainTarget domainEnhance model performanceMM-WHSData distributionSegmentation performanceTarget samplesMixupMS-CMRSegConsistency alignmentClass awarenessExperimental resultsClass-Aware Mutual Mixup with Triple Alignments for Semi-supervised Cross-Domain Segmentation
Cai, Zhuotong, et al. "Class-Aware Mutual Mixup with Triple Alignments for Semi-supervised Cross-Domain Segmentation." International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2024.Peer-Reviewed Original ResearchPerformance Characteristics of the NeuroEXPLORER, a Next-Generation Human Brain PET/CT Imager
Li H, Badawi R, Cherry S, Fontaine K, He L, Henry S, Hillmer A, Hu L, Khattar N, Leung E, Li T, Li Y, Liu C, Liu P, Lu Z, Majewski S, Matuskey D, Morris E, Mulnix T, Omidvari N, Samanta S, Selfridge A, Sun X, Toyonaga T, Volpi T, Zeng T, Jones T, Qi J, Carson R. Performance Characteristics of the NeuroEXPLORER, a Next-Generation Human Brain PET/CT Imager. Journal Of Nuclear Medicine 2024, 65: jnumed.124.267767. PMID: 38871391, PMCID: PMC11294061, DOI: 10.2967/jnumed.124.267767.Peer-Reviewed Original ResearchPeak noise-equivalent count rateNoise-equivalent count rateTime-of-flight resolutionField of viewCount rateExtended axial field-of-viewTransverse field-of-viewAxial field-of-viewField-of-view centerMini-Derenzo phantomSpatial resolutionTangential spatial resolutionsCount rate performanceContrast recovery coefficientHuman brain PET imagingMeasurements of spatial resolutionNEMA sensitivityEnergy resolutionScatter fractionBrain phantomBackprojection reconstructionBrain PET imagingTime resolutionRadial offsetF-FDG imagingThe Software System of a Dedicated Brain PET Scanner Using Dual-Ended Readout Detectors With High-DOI Resolution
Liu J, Ren N, Zeng T, Kuang Z, Zhang Q, Wang X, Liu Z, Zheng H, Liang D, Yang Y, Hu Z. The Software System of a Dedicated Brain PET Scanner Using Dual-Ended Readout Detectors With High-DOI Resolution. IEEE Transactions On Radiation And Plasma Medical Sciences 2024, 8: 655-663. DOI: 10.1109/trpms.2024.3370308.Peer-Reviewed Original ResearchPositron emission tomography scannerDepth of interactionBrain PET scannerPET scannerDetector calibrationDual-ended readout detectorWhole-body PET scannerDepth-encoding detectorsHoffman brain phantomCrystal Look-up tableMeasured singlesReadout detectorsCount rateAxial fieldBrain phantomBrain positron emission tomographyRadial offsetDetectorLook-up tableSoftware systemsCrystal energyImaging capabilitiesData acquisition systemGraphics processing unit accelerationSpatial resolutionThe Software System of a Dedicated Brain PET Scanner Using Dual-Ended Readout Detectors With High DOI Resolution
Liu J, Ren N, Zeng T, Kuang Z, Zhang Q, Wang X, Liu Z, Zheng H, Liang D, Yang Y, Hu Z. The Software System of a Dedicated Brain PET Scanner Using Dual-Ended Readout Detectors With High DOI Resolution. IEEE Transactions on Radiation and Plasma Medical Sciences. 2024 Feb 26.Peer-Reviewed Original Research
2023
Markerless head motion tracking and event-by-event correction in brain PET
Zeng T, Lu Y, Jiang W, Zheng J, Zhang J, Gravel P, Wan Q, Fontaine K, Mulnix T, Jiang Y, Yang Z, Revilla E, Naganawa M, Toyonaga T, Henry S, Zhang X, Cao T, Hu L, Carson R. Markerless head motion tracking and event-by-event correction in brain PET. Physics In Medicine And Biology 2023, 68: 245019. PMID: 37983915, PMCID: PMC10713921, DOI: 10.1088/1361-6560/ad0e37.Peer-Reviewed Original ResearchConceptsPoint source studyHead motion correctionSmaller residual displacementMotion correctionIterative closest point (ICP) registration algorithmHead motion trackingSpatial resolutionResidual displacementData-driven evaluation methodHigh spatial resolutionLow noiseMotion trackingStereovision cameraMotion tracking deviceStructured lightEvent correctionBrain positron emission tomography (PET) imagingTracking deviceReconstruction resultsHMT methodPoint cloudsNegative biasReference cloudUMTEvaluation methodUnsupervised 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 alignment
Academic Achievements & Community Involvement
News & Links
News
Get In Touch
Contacts
Email
Locations
100 Church Street South
Academic Office
New Haven, CT 06519