2022
Machine learning to predict abnormal myocardial perfusion from pre-test features
Miller RJH, Hauser MT, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Huang C, Liang JX, Han D, Dey D, Berman DS, Slomka PJ. Machine learning to predict abnormal myocardial perfusion from pre-test features. Journal Of Nuclear Cardiology 2022, 29: 2393-2403. PMID: 35672567, PMCID: PMC9588501, DOI: 10.1007/s12350-022-03012-6.Peer-Reviewed Original ResearchConceptsAbnormal myocardial perfusionAbnormal perfusionMyocardial perfusionDiamond-Forrester modelCAD consortiumConsecutive patientsInternational registryPre-test informationSPECT-MPIClinical informationPhysician's decisionPatientsPerfusionTesting populationExpert visual interpretationRegistryPopulationMethodsWePhysicians
2021
Diagnostic 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