Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death
Kulkarni PM, Robinson EJ, Pradhan J, Gartrell-Corrado RD, Rohr BR, Trager MH, Geskin LJ, Kluger HM, Wong PF, Acs B, Rizk EM, Yang C, Mondal M, Moore MR, Osman I, Phelps R, Horst BA, Chen ZS, Ferringer T, Rimm DL, Wang J, Saenger YM. Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death. Clinical Cancer Research 2019, 26: 1126-1134. PMID: 31636101, PMCID: PMC8142811, DOI: 10.1158/1078-0432.ccr-19-1495.Peer-Reviewed Original ResearchMeSH KeywordsAdultAgedAged, 80 and overAlgorithmsArea Under CurveBiopsyDeep LearningDisease ProgressionFemaleFollow-Up StudiesHumansImage Processing, Computer-AssistedMaleMelanomaMiddle AgedNeoplasm Recurrence, LocalNeural Networks, ComputerRetrospective StudiesRisk FactorsStaining and LabelingSurvival RateYoung AdultConceptsDeep neural network architectureNeural network architectureDeep learningNetwork architectureComputational modelImage sequencesDigital imagesVote aggregationDisease-specific survivalDSS predictionPractical advancesComputational methodsIHC-based methodsImagesGeisinger Health SystemNovel methodGHS patientsArchitectureLearningKaplan-Meier analysisPrimary melanoma tumorsEarly-stage melanomaClinical trial designModelAdjuvant immunotherapy