2024
Noise-aware dynamic image denoising and positron range correction for Rubidium-82 cardiac PET imaging via self-supervision
Xie H, Guo L, Velo A, Liu Z, Liu Q, Guo X, Zhou B, Chen X, Tsai Y, Miao T, Xia M, Liu Y, Armstrong I, Wang G, Carson R, Sinusas A, Liu C. Noise-aware dynamic image denoising and positron range correction for Rubidium-82 cardiac PET imaging via self-supervision. Medical Image Analysis 2024, 100: 103391. PMID: 39579623, DOI: 10.1016/j.media.2024.103391.Peer-Reviewed Original ResearchImage denoisingPositron range correctionDynamic framesSelf-supervised methodsSuperior visual qualityLow signal-to-noise ratioCardiac PET imagingDenoising methodSignal-to-noise ratioSelf-supervisionVisual qualityHigh-energy positronsRange correctionsDenoisingNoise levelImage spatial resolutionImage qualityDefect contrastPET imagingImage quantificationRadioactive isotopesPatient scansQuantitative accuracyImagesFrameReproducibility for quantification of myocardial Tc-99m PYP amyloid uptake in grade 1 patients
Sandoval V, Goyal D, Miller E, Liu Y. Reproducibility for quantification of myocardial Tc-99m PYP amyloid uptake in grade 1 patients. European Heart Journal - Cardiovascular Imaging 2024, 25: jeae142.047. DOI: 10.1093/ehjci/jeae142.047.Peer-Reviewed Original ResearchStandardized uptake valueTc-99m PYP uptakeTc-99Cardiac amyloidosisHeart failureStandard uptake value quantificationStandardized uptake value calculationSPECT imagesIntractable heart failureSystolic heart failureIntroduction of therapyPlanar imagingTc-99m pyrophosphateAmyloid patientsSPECT/CT imagingInter-reproducibilityUptake valueContralateral ratioCoefficient of variationDisease progressionH/M ratioGrade 1Blood poolPatientsH/CL ratioTAI-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 disease
2023
CT attenuation correction improves quantitative risk prediction by cardiac SPECT in obese patients
Feher A, Pieszko K, Shanbhag A, Lemley M, Bednarski B, Miller R, Huang C, Miras L, Liu Y, Sinusas A, Slomka P, Miller E. CT attenuation correction improves quantitative risk prediction by cardiac SPECT in obese patients. European Journal Of Nuclear Medicine And Molecular Imaging 2023, 51: 695-706. PMID: 37924340, DOI: 10.1007/s00259-023-06484-x.Peer-Reviewed Original ResearchMajor adverse cardiac eventsMyocardial perfusion imagingSPECT myocardial perfusion imagingMACE-free survivalObese patientsPrognostic valueSignificant incremental prognostic valueYale-New Haven HospitalLate coronary revascularizationStress total perfusion deficitAdverse cardiac eventsIncremental prognostic valueNonfatal myocardial infarctionComposite end pointCT myocardial perfusion imagingSuperior prognostic valueSPECT/CT myocardial perfusion imagingTotal perfusion deficitNew Haven HospitalCT attenuation correctionHighest ROC areaStress TPDCoronary revascularizationCardiac eventsPatient populationComparison of the prognostic value between quantification and visual estimation of coronary calcification from attenuation CT in patients undergoing SPECT myocardial perfusion imaging
Feher A, Pieszko K, Shanbhag A, Lemley M, Miller R, Huang C, Miras L, Liu Y, Gerber J, Sinusas A, Miller E, Slomka P. Comparison of the prognostic value between quantification and visual estimation of coronary calcification from attenuation CT in patients undergoing SPECT myocardial perfusion imaging. The International Journal Of Cardiovascular Imaging 2023, 40: 185-193. PMID: 37845406, PMCID: PMC466934, DOI: 10.1007/s10554-023-02980-1.Peer-Reviewed Original ResearchConceptsMajor adverse cardiovascular eventsCoronary artery calcificationMyocardial perfusion imagingCT myocardial perfusion imagingSPECT/CT myocardial perfusion imagingArtery calcificationPrognostic valuePrior coronary stentingAdverse cardiovascular eventsSimilar prognostic valueSPECT myocardial perfusionREFINE SPECT registrySPECT/CTCardiovascular eventsCAC scoringCalcium scoreCoronary calcificationCoronary stentingPrognostic utilitySingle centerCoronary arteryLow doseMyocardial perfusionPerfusion imagingSurvival analysisTAI-GAN: Temporally and Anatomically Informed GAN for Early-to-Late Frame Conversion in Dynamic Cardiac PET Motion Correction
Guo X, Shi L, Chen X, Zhou B, Liu Q, Xie H, Liu Y, Palyo R, Miller E, Sinusas A, Spottiswoode B, Liu C, Dvornek N. TAI-GAN: Temporally and Anatomically Informed GAN for Early-to-Late Frame Conversion in Dynamic Cardiac PET Motion Correction. Lecture Notes In Computer Science 2023, 14288: 64-74. PMID: 38464964, PMCID: PMC10923183, DOI: 10.1007/978-3-031-44689-4_7.Peer-Reviewed Original ResearchTransformer-Based Dual-Domain Network for Few-View Dedicated Cardiac SPECT Image Reconstructions
Xie H, Zhou B, Chen X, Guo X, Thorn S, Liu Y, Wang G, Sinusas A, Liu C. Transformer-Based Dual-Domain Network for Few-View Dedicated Cardiac SPECT Image Reconstructions. Lecture Notes In Computer Science 2023, 14229: 163-172. DOI: 10.1007/978-3-031-43999-5_16.Peer-Reviewed Original ResearchDual-domain networkSPECT image reconstructionImage reconstructionDeep learning methodsPrevious baseline methodsCardiac SPECT imagesHigh-quality imagesReconstruction networkIterative reconstruction processView reconstructionBaseline methodsReconstruction outputLearning methodsClinical softwareReconstruction processImaging problemsProjection dataImage qualityNetworkImagesStationary dataSPECT scannerDiagnosis of CVDLimited amountSoftwareCorrection to: Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging
Feher A, Pieszko K, Miller R, Lemley M, Shanbhag A, Huang C, Miras L, Liu Y, Sinusas A, Miller E, Slomka P. Correction to: Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging. Journal Of Nuclear Cardiology 2023, 30: 860-863. PMID: 36598750, DOI: 10.1007/s12350-022-03196-x.Peer-Reviewed Original ResearchCORONARY ARTERY CALCIFICATIONS ARE A BETTER PREDICTOR OF CARDIOVASCULAR OUTCOMES THAN ISCHEMIC ECG CHANGES IN PATIENTS WITH NORMAL PERFUSION ON EXERCISE SPECT
Shi T, Kokkinidis D, Agarwal R, Liu Y, Sinusas A, Miller E, Feher A. CORONARY ARTERY CALCIFICATIONS ARE A BETTER PREDICTOR OF CARDIOVASCULAR OUTCOMES THAN ISCHEMIC ECG CHANGES IN PATIENTS WITH NORMAL PERFUSION ON EXERCISE SPECT. Journal Of The American College Of Cardiology 2023, 81: 1498. DOI: 10.1016/s0735-1097(23)01942-3.Peer-Reviewed Original ResearchIN PATIENTS UNDERGOING NUCLEAR MYOCARDIAL PERFUSION IMAGING, RHEUMATOID ARTHRITIS IS ASSOCIATED WITH INCREASED RISK OF ADVERSE CARDIOVASCULAR EVENTS INDEPENDENT OF MYOCARDIAL ISCHEMIA
Pires J, Oikonomou E, Agarwal R, Liu Y, miller E, Sinusas A, Feher A. IN PATIENTS UNDERGOING NUCLEAR MYOCARDIAL PERFUSION IMAGING, RHEUMATOID ARTHRITIS IS ASSOCIATED WITH INCREASED RISK OF ADVERSE CARDIOVASCULAR EVENTS INDEPENDENT OF MYOCARDIAL ISCHEMIA. Journal Of The American College Of Cardiology 2023, 81: 1467. DOI: 10.1016/s0735-1097(23)01911-3.Peer-Reviewed Original ResearchFast myocardial perfusion SPECT denoising using an attention-guided generative adversarial network
Sun J, Yang B, Li C, Du Y, Liu Y, Wu T, Mok G. Fast myocardial perfusion SPECT denoising using an attention-guided generative adversarial network. Frontiers In Medicine 2023, 10: 1083413. PMID: 36817784, PMCID: PMC9935600, DOI: 10.3389/fmed.2023.1083413.Peer-Reviewed Original ResearchAttention-guided generative adversarial networkGenerative adversarial networkAdversarial networkConvolutional neural network (CNN)-based methodsDeep learning-based denoisersCNN-based networkLearning-based denoisingLocal receptive fieldsReceptive fieldsAttention mechanismConvolution kernelAdam optimizerFive-fold cross-validationAttGANAcquisition timeList mode dataJoint histogramPerfusion defect sizeCGANDefect informationUNetDenoisingNetworkMP-SPECTProjection pairs
2022
High-Resolution and High-Sensitivity Spread Field Imaging to Differentiate Sub-endocardium and Sub-epicardium in Cardiac SPECT — A Preliminary Phantom Study
Mu Z, Palyo R, Goyal D, Sandoval V, Mu Z, Tao Z, Sinusas A, Miller E, Liu Y. High-Resolution and High-Sensitivity Spread Field Imaging to Differentiate Sub-endocardium and Sub-epicardium in Cardiac SPECT — A Preliminary Phantom Study. 2022, 00: 1-4. DOI: 10.1109/nss/mic44845.2022.10399016.Peer-Reviewed Original ResearchTc-99m solutionHole imagesCardiac SPECTCardiac phantomMyocardial perfusion defectsField imagesParallel hole collimatorResolution of SPECTSub-endocardiumSubset expectation maximizationCZT detectorsSub-epicardiumHole collimatorPerfusion defectsHigh-resolutionOSEM algorithmCollimatorPhantom studyScanner configurationReconstruction technologyPhantomSPECT slicesTransmural perfusion gradientExpectation maximizationOSEMLow Dose Myocardial Perfusion SPECT Denoising Using an Attention-Based Generative Adversarial Network
Sun J, Li C, Du Y, Wu T, Yang B, Liu Y, Mok G. Low Dose Myocardial Perfusion SPECT Denoising Using an Attention-Based Generative Adversarial Network. 2022, 00: 1-3. DOI: 10.1109/nss/mic44845.2022.10399080.Peer-Reviewed Original ResearchNormalized Mean Square ErrorConvolutional neural network (CNN)-based methodsDeep learning-based denoisersConditional generative adversarial networkKernel’s receptive fieldLearning-based denoisingGenerative adversarial networkProjection-domainReceptive fieldsMean square errorList mode dataDenoising performanceAttention schemeAdversarial networkConvolution kernelAdam optimizerPerfusion defect sizeDenoisingNormalized standard deviationFull doseCGANMP-SPECTDose levelsLow dosesSquare errorIntegration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging
Feher A, Pieszko K, Miller R, Lemley M, Shanbhag A, Huang C, Miras L, Liu YH, Sinusas AJ, Miller EJ, Slomka PJ. Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging. Journal Of Nuclear Cardiology 2022, 30: 590-603. PMID: 36195826, DOI: 10.1007/s12350-022-03099-x.Peer-Reviewed Original ResearchConceptsMajor adverse cardiovascular eventsMyocardial perfusion imagingAdverse cardiovascular eventsSPECT myocardial perfusion imagingCAC scoringCardiovascular eventsPrediction of MACECoronary artery calcification (CAC) scoringMACE-free survivalClinical risk factorsCoronary artery calciumCT myocardial perfusion imagingReceiver operator characteristic curveSPECT/CT myocardial perfusion imagingSPECT/CTOperator characteristic curveCT myocardial perfusionArtery calciumCAC scoreAnalysis patientsMACE predictionSingle centerHigher event ratesRisk factorsRisk scoreDeep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion SPECT
Du Y, Shang J, Sun J, Wang L, Liu YH, Xu H, Mok GSP. Deep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion SPECT. Journal Of Nuclear Cardiology 2022, 30: 1022-1037. PMID: 36097242, DOI: 10.1007/s12350-022-03092-4.Peer-Reviewed Original ResearchPotential Impact of SPECT Resolution on Quantification of Left Ventricular Volumes and Ejection Fraction: A Phantom Study
Liu H, Aslan M, Sandoval V, Liu Y. Potential Impact of SPECT Resolution on Quantification of Left Ventricular Volumes and Ejection Fraction: A Phantom Study. Journal Of Medical And Biological Engineering 2022, 42: 734-743. DOI: 10.1007/s40846-022-00747-y.Peer-Reviewed Original ResearchImage resolutionCurrent software toolsDifferent image resolutionsLow resolutionSoftware toolsEmory Cardiac ToolboxPartial volume effectsSoftwareQuantitative softwarePhantom volumeImagesAttenuation correctionSPECT resolutionDedicated cardiac SPECT cameraDual-head SPECTCameraHigh resolutionCardiac phantomQuantification softwareDeep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT
Sun J, Jiang H, Du Y, Li C, Wu T, Liu Y, Yang B, Mok G. Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT. Journal Of Nuclear Cardiology 2022, 30: 970-985. PMID: 35982208, DOI: 10.1007/s12350-022-03045-x.Peer-Reviewed Original ResearchConceptsConditional generative adversarial networkGenerative adversarial networkImage qualityAdversarial networkOS-EM methodList-mode dataXCAT phantomPost-reconstruction filteringImagesSPECT projectionsDenoisingMyocardial perfusion SPECTHigh noise levelsPerfusion SPECTFull doseSPECT/CT scansNetworkDifferent anatomical variationsMode dataFilteringMP-SPECTLD imagesDeep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer
Xie H, Thorn S, Liu Y, Lee S, Liu Z, Wang G, Sinusas A, Liu C. Deep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer. IEEE Transactions On Radiation And Plasma Medical Sciences 2022, 7: 33-40. PMID: 37397179, PMCID: PMC10312390, DOI: 10.1109/trpms.2022.3187595.Peer-Reviewed Original ResearchConvolutional neural networkLimitations of CNNMedical imaging tasksDeep U-NetImage reconstruction taskCardiac SPECT imagesComputer visionVision TransformerConvolutional kernelsTransformer networkAttention blockInput imageU-NetNeural networkMemory burdenImage sizeInductive biasInformative featuresImage volumesImaging tasksTesting dataNetworkWhole 3D volumeNetwork structureCardiac single photon emissionIncreasing angular sampling through deep learning for stationary cardiac SPECT image reconstruction
Xie H, Thorn S, Chen X, Zhou B, Liu H, Liu Z, Lee S, Wang G, Liu YH, Sinusas AJ, Liu C. Increasing angular sampling through deep learning for stationary cardiac SPECT image reconstruction. Journal Of Nuclear Cardiology 2022, 30: 86-100. PMID: 35508796, DOI: 10.1007/s12350-022-02972-z.Peer-Reviewed Original ResearchConceptsDeep learningReconstruction qualityImage reconstructionDeep learning methodsDeep neural networksDeep learning resultsImage qualityNetwork trainingSPECT image reconstructionNeural networkLearning methodsHigh image resolutionImage volumesClinical softwareImage metricsImage resolutionReconstruction resultsImproved image qualityTesting dataLearning resultsNetwork resultsPhysical phantomStationary imagingDifferent subjectsLearningCross-vender, cross-tracer, and cross-protocol deep transfer learning for attenuation map generation of cardiac SPECT
Chen X, Pretorius P, Zhou B, Liu H, Johnson K, Liu YH, King MA, Liu C. Cross-vender, cross-tracer, and cross-protocol deep transfer learning for attenuation map generation of cardiac SPECT. Journal Of Nuclear Cardiology 2022, 29: 3379-3391. PMID: 35474443, PMCID: PMC11407548, DOI: 10.1007/s12350-022-02978-7.Peer-Reviewed Original Research