{"id":"W4366281042","doi":"10.3390/jimaging9040084","title":"Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review","year":2023,"lang":"en","type":"review","venue":"Journal of Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Deep learning; Convolutional neural network; Macular degeneration; Modalities; Artificial intelligence; Glaucoma; Diabetic retinopathy; Retinal; Grading (engineering); Retinal Disorder; Blindness; CAD; Machine learning; Optometry; Medicine; Ophthalmology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00101736,0.0004234015,0.002745333,0.0009563249,0.0001528539,0.00007510513,0.0001936708,0.00007022109,0.00002910588],"category_scores_gemma":[0.001051491,0.0003167574,0.001933966,0.001052028,0.0000812474,0.0001720491,0.00008149457,0.001747826,0.00003010932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003784222,"about_ca_system_score_gemma":0.000387819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001092092,"about_ca_topic_score_gemma":1.416831e-7,"domain_scores_codex":[0.9967365,0.0004267286,0.001572163,0.0003016024,0.0006409724,0.0003219843],"domain_scores_gemma":[0.9960799,0.0001978279,0.002323825,0.0002826971,0.0007737498,0.0003420497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001812347,0.00002294999,0.00006401438,0.09297697,0.0003323989,0.001853158,0.00001099714,0.000002512513,0.000030929,2.698775e-7,0.0001162639,0.9045714],"study_design_scores_gemma":[0.0001078155,0.00004472825,0.000009112055,0.3621552,0.01249055,0.005629718,0.00004899633,0.0005446793,0.000004240861,0.000007330264,0.618744,0.0002137015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000010996,0.9955503,0.003515919,0.0002565523,0.0001577633,0.0003461824,0.00000161621,0.00009309419,0.00006761518],"genre_scores_gemma":[0.0000153416,0.9957802,0.002828139,0.0002425555,0.0008477442,0.000007569439,0.00001302762,0.0001142323,0.0001512412],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9043577,"threshold_uncertainty_score":0.9999285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07344503460586009,"score_gpt":0.4173284557208994,"score_spread":0.3438834211150393,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}