Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration
Chen Q, Keenan T, Allot A, Peng Y, Agrón E, Domalpally A, Klaver C, Luttikhuizen D, Colyer M, Cukras C, Wiley H, Magone M, Cousineau-Krieger C, Wong W, Zhu Y, Chew E, Lu Z, Group F. Multimodal, multitask, multiattention (M3) deep learning detection of reticular pseudodrusen: Toward automated and accessible classification of age-related macular degeneration. Journal Of The American Medical Informatics Association 2021, 28: 1135-1148. PMID: 33792724, PMCID: PMC8200273, DOI: 10.1093/jamia/ocaa302.Peer-Reviewed Original ResearchMeSH KeywordsAgedComputer SimulationDatasets as TopicDeep LearningDiagnosis, Computer-AssistedFemaleFundus OculiHumansMacular DegenerationMaleRetinal DrusenConceptsColor fundus photographyAge-related macular degenerationFundus autofluorescenceReticular pseudodrusenMacular degenerationStandard color fundus photographyReceiver-operating characteristic curveAdvanced imaging modalitiesExternal validationRetinal specialistsAMD featuresFundus photographyGeographic atrophyPigmentary abnormalitiesAMD diagnosisImaging modalitiesCharacteristic curvePseudodrusenDegeneration