{"id":"W4409944661","doi":"10.35882/jeeemi.v7i2.706","title":"A Novel Deep Learning Framework for Enhanced Glaucoma Detection Using Attention-Gated U-Net, Deep Wavelet Scattering, and Vision Transformers","year":2025,"lang":"en","type":"article","venue":"Journal of Electronics Electromedical Engineering and Medical Informatics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Glaucoma; Transformer; Artificial intelligence; Wavelet; Computer science; Pattern recognition (psychology); Medicine; Engineering; Ophthalmology; Electrical engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001007899,0.0002308606,0.0006176416,0.0004786733,0.0001518398,0.00006079484,0.00009763471,0.0003020304,0.000009194348],"category_scores_gemma":[0.00141024,0.0001901638,0.000193606,0.0004882691,0.000111706,0.0001814009,0.00002509463,0.001502195,2.348217e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887516,"about_ca_system_score_gemma":0.000257335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004306844,"about_ca_topic_score_gemma":0.000002458796,"domain_scores_codex":[0.9977393,0.00002012295,0.0009688124,0.0001303986,0.000599583,0.000541823],"domain_scores_gemma":[0.9986567,0.0003266463,0.000270688,0.0000812553,0.0002170934,0.0004476012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000815743,0.0003405334,0.0002866534,0.003112814,0.001739232,0.00002452878,0.001003123,0.001052843,0.3052687,0.001211468,0.00002606925,0.6851183],"study_design_scores_gemma":[0.002475409,0.001445193,0.0003763559,0.001676548,0.0005956966,0.001094216,0.0002169947,0.982927,0.006837961,0.0001996765,0.001960487,0.0001945168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4175169,0.00109003,0.5807192,0.0004665552,0.00007721993,0.00009240081,2.768193e-7,0.00002383899,0.00001362147],"genre_scores_gemma":[0.9507316,0.002910075,0.04575899,0.0003741986,0.0001604837,0.000004939026,0.000009031421,0.00002479361,0.00002584192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818741,"threshold_uncertainty_score":0.7754654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003977467642453081,"score_gpt":0.2730013660069847,"score_spread":0.2690238983645316,"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."}}