2023
DuSFE: Dual-Channel Squeeze-Fusion-Excitation co-attention for cross-modality registration of cardiac SPECT and CT
Chen X, Zhou B, Xie H, Guo X, Zhang J, Duncan J, Miller E, Sinusas A, Onofrey J, Liu C. DuSFE: Dual-Channel Squeeze-Fusion-Excitation co-attention for cross-modality registration of cardiac SPECT and CT. Medical Image Analysis 2023, 88: 102840. PMID: 37216735, PMCID: PMC10524650, DOI: 10.1016/j.media.2023.102840.Peer-Reviewed Original ResearchConceptsCross-modality registrationConvolutional layersCo-attention mechanismMultiple convolutional layersCo-attention moduleDifferent convolutional layersMedical image registrationInput data streamDeep learning strategiesLow registration errorIntensity-based registration methodCardiac SPECTΜ-mapsDeep learningFeature fusionData streamsInput imageSource codeFeature mapsNeural networkImage registrationSpatial featuresRegistration performanceRegistration methodInput information
2022
Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events
Pieszko K, Shanbhag A, Killekar A, Miller RJH, Lemley M, Otaki Y, Singh A, Kwiecinski J, Gransar H, Van Kriekinge SD, Kavanagh PB, Miller EJ, Bateman T, Liang JX, Berman DS, Dey D, Slomka PJ. Deep Learning of Coronary Calcium Scores From PET/CT Attenuation Maps Accurately Predicts Adverse Cardiovascular Events. JACC Cardiovascular Imaging 2022, 16: 675-687. PMID: 36284402, DOI: 10.1016/j.jcmg.2022.06.006.Peer-Reviewed Original Research
2021
Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study
Torkaman M, Yang J, Shi L, Wang R, Miller EJ, Sinusas AJ, Liu C, Gullberg GT, Seo Y. Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study. IEEE Transactions On Radiation And Plasma Medical Sciences 2021, 6: 755-765. PMID: 36059429, PMCID: PMC9438341, DOI: 10.1109/trpms.2021.3138372.Peer-Reviewed Original ResearchData management strategiesTraining dataAdvanced networksDeep learning techniquesConventional U-NetRepresentation of dataSimilarity of dataDeep learningLearning techniquesGAN networkData managementDL modelsU-NetPerformance variabilityNetworkDimensional spaceAttenuation correctionEffective trainingCardiac SPECTGlobal performanceImagesTaskLearningTrainingSpaceAutomatic Inter-Frame Patient Motion Correction for Dynamic Cardiac PET Using Deep Learning
Shi L, Lu Y, Dvornek N, Weyman CA, Miller EJ, Sinusas AJ, Liu C. Automatic Inter-Frame Patient Motion Correction for Dynamic Cardiac PET Using Deep Learning. IEEE Transactions On Medical Imaging 2021, 40: 3293-3304. PMID: 34018932, PMCID: PMC8670362, DOI: 10.1109/tmi.2021.3082578.Peer-Reviewed Original ResearchConceptsConvolutional neural networkRegistration-based methodMotion correctionDynamic frameTracer distribution changeDynamic image dataPatient motion correctionPatient scansDeep learningPatient motionMotion estimationImage dataLSTM networkNeural networkRealistic patient motionTemporal informationMotion correction methodMotion detectionCardiac PETClinical workflowRigid translational motionFlow estimationNetworkPatient datasetsSuperior performanceDiagnostic accuracy of stress-only myocardial perfusion SPECT improved by deep learning
Liu H, Wu J, Miller EJ, Liu C, Yaqiang, Liu, Liu YH. Diagnostic accuracy of stress-only myocardial perfusion SPECT improved by deep learning. European Journal Of Nuclear Medicine And Molecular Imaging 2021, 48: 2793-2800. PMID: 33511425, DOI: 10.1007/s00259-021-05202-9.Peer-Reviewed Original ResearchConceptsMyocardial perfusion imagingCoronary artery diseaseMyocardial perfusion abnormalitiesPerfusion abnormalitiesDiagnostic accuracyConvolutional neural networkTomography myocardial perfusion imagingYale-New Haven HospitalMyocardial perfusion defect sizeSPECT myocardial perfusion imagingAbnormal myocardial perfusionReceiver-operating characteristic curvePerfusion defect sizeNew Haven HospitalAUC valuesSingle photon emissionMyocardial perfusion SPECTDeep learningHigh diagnostic accuracyArtery diseaseDL methodsFinal diagnosisPatient genderMyocardial perfusionPerfusion SPECT