2024
Artificial Intelligence Predicts Hospitalization for Acute Heart Failure Exacerbation in Patients Undergoing Myocardial Perfusion Imaging
Feher A, Bednarski B, Miller R, Shanbhag A, Lemley M, Miras L, Sinusas A, Miller E, Slomka P. Artificial Intelligence Predicts Hospitalization for Acute Heart Failure Exacerbation in Patients Undergoing Myocardial Perfusion Imaging. Journal Of Nuclear Medicine 2024, 65: jnumed.123.266761. PMID: 38548351, PMCID: PMC11064832, DOI: 10.2967/jnumed.123.266761.Peer-Reviewed Original ResearchConceptsMyocardial perfusion imagingHF hospitalizationHeart failureStress left ventricular ejection fractionPerfusion imagingHF exacerbationPredictive of HF hospitalizationsSPECT/CT myocardial perfusion imagingMyocardial perfusionInternational cohortAcute heart failure exacerbationMedian follow-upVentricular ejection fractionReceiver-operating-characteristic curveClinical risk factorsHeart failure exacerbationExternal validation cohortAcute HF exacerbationPrevent HF hospitalizationsImaging parametersCalcium scoreEjection fractionClinical parametersCT scanValidation cohort
2022
Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion SPECT images
Miller RJH, Singh A, Otaki Y, Tamarappoo BK, Kavanagh P, Parekh T, Hu LH, Gransar H, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli MF, Liang JX, Dey D, Berman DS, Slomka PJ. Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion SPECT images. European Journal Of Nuclear Medicine And Molecular Imaging 2022, 50: 387-397. PMID: 36194270, PMCID: PMC10042590, DOI: 10.1007/s00259-022-05972-w.Peer-Reviewed Original ResearchConceptsCoronary artery diseaseMyocardial perfusion imagingArtery diseaseInvasive angiographyObstructive coronary artery diseaseDisease probabilityLow-risk patientsLow-risk populationHigh-risk populationTotal perfusion deficitHigh diagnostic accuracyS-TPDPerfusion deficitsPatient managementPatientsPerfusion imagingDiagnostic accuracyPerfusion SPECT imagesLower likelihoodGood calibrationCharacteristic curveAngiographySPECT imagesSelection biasDiseaseExplainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging.
Miller RJH, Kuronuma K, Singh A, Otaki Y, Hayes S, Chareonthaitawee P, Kavanagh P, Parekh T, Tamarappoo BK, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Carli MD, Cadet S, Liang JX, Dey D, Berman DS, Slomka PJ. Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging. Journal Of Nuclear Medicine 2022, 63: 1768-1774. PMID: 35512997, PMCID: PMC9635672, DOI: 10.2967/jnumed.121.263686.Peer-Reviewed Original ResearchMeSH KeywordsArtificial IntelligenceCoronary AngiographyCoronary Artery DiseaseDeep LearningHumansMyocardial Perfusion ImagingPhysiciansTomography, Emission-Computed, Single-PhotonConceptsMyocardial perfusion imagingCoronary artery diseaseObstructive coronary artery diseasePhysician interpretationDiagnostic accuracyPerfusion imagingLeft main arteryOverall net reclassification improvementInvasive coronary angiographyNet reclassification improvementTotal perfusion deficitArtery diseaseCoronary angiographyMedian agePhysician diagnosisReclassification improvementPerfusion deficitsClinical historyCoronary segmentsRepresentative cohortMeaningful improvementsMain arteryPatientsDL resultsQuantitative perfusion
2021
Clinical Deployment of Explainable Artificial Intelligence of SPECT for Diagnosis of Coronary Artery Disease
Otaki Y, Singh A, Kavanagh P, Miller RJH, Parekh T, Tamarappoo BK, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Cadet S, Liang JX, Dey D, Berman DS, Slomka PJ. Clinical Deployment of Explainable Artificial Intelligence of SPECT for Diagnosis of Coronary Artery Disease. JACC Cardiovascular Imaging 2021, 15: 1091-1102. PMID: 34274267, PMCID: PMC9020794, DOI: 10.1016/j.jcmg.2021.04.030.Peer-Reviewed Original ResearchConceptsTotal perfusion deficitMyocardial perfusion imagingStandard clinical softwareStress total perfusion deficitObstructive CADTomography myocardial perfusion imagingSPECT myocardial perfusion imagingStress myocardial perfusionCoronary artery diseaseReceiver-operating characteristic curveInvasive coronary angiographyClinical softwareReader diagnosisSingle photon emissionTypical clinical workflowArtery diseaseCoronary angiographyPerfusion deficitsDiagnostic findingsMyocardial perfusionPerfusion imagingVentricular volumeStandard clinical workstationPatientsDiagnostic accuracy
2018
Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT)
Slomka PJ, Betancur J, Liang JX, Otaki Y, Hu LH, Sharir T, Dorbala S, Di Carli M, Fish MB, Ruddy TD, Bateman TM, Einstein AJ, Kaufmann PA, Miller EJ, Sinusas AJ, Azadani PN, Gransar H, Tamarappoo BK, Dey D, Berman DS, Germano G. Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT). Journal Of Nuclear Cardiology 2018, 27: 1010-1021. PMID: 29923104, PMCID: PMC6301135, DOI: 10.1007/s12350-018-1326-4.Peer-Reviewed Original ResearchMeSH KeywordsAgedArtificial IntelligenceAutomationCoronary AngiographyCoronary Artery DiseaseData CollectionDatabases, FactualFemaleFollow-Up StudiesHumansImage Processing, Computer-AssistedMachine LearningMaleMiddle AgedMyocardial Perfusion ImagingPrognosisRegistriesReproducibility of ResultsSoftwareTomography, Emission-Computed, Single-PhotonConceptsMyocardial perfusion imagingPharmacologic stressMajor adverse cardiac eventsAdverse cardiac eventsRevascularization resultsMulticenter registryCardiac eventsClinical variablesPrognostic outcomesResultsTo dateClinical dataPrognostic dataDiagnostic cohortSPECT-MPIImaging variablesMyocardial perfusionPrognostic cohortPerfusion imagingPatientsRegistryArtificial intelligence toolsNew artificial intelligence toolsQuantitative softwareCohortClinical image database