{"id":"W3210027215","doi":"10.1016/j.media.2021.102295","title":"Diagnosing glaucoma on imbalanced data with self-ensemble dual-curriculum learning","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Science and Technology Project of Nantong City; Fundamental Research Funds for Central Universities of the Central South University; National Key Research and Development Program of China; Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Glaucoma; Artificial intelligence; Computer science; Feature (linguistics); Discriminative model; Weighting; Machine learning; Pattern recognition (psychology); Feature vector; Feature learning; Medicine; Ophthalmology; Radiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001685709,0.001241574,0.001215774,0.001453355,0.0005319686,0.0007803548,0.001085341,0.001418487,0.00105998],"category_scores_gemma":[0.003503783,0.0003483584,0.001355815,0.0008321012,0.0003530581,0.001362537,0.001853558,0.001469483,0.0005737618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003415916,"about_ca_system_score_gemma":0.0007912612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002947544,"about_ca_topic_score_gemma":0.004747482,"domain_scores_codex":[0.9992914,0.0001309971,0.00005261823,0.0002673143,0.0001327475,0.0001248839],"domain_scores_gemma":[0.9983279,0.0008066171,0.0001015892,0.0002378891,0.0004033003,0.0001225996],"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":[0.001053031,0.001280445,0.03543713,0.0002111846,0.0004956726,0.0003255639,0.0002244377,0.1038445,0.02294227,0.0009473352,0.0087112,0.8245272],"study_design_scores_gemma":[0.00003098375,0.0002432102,0.005932454,0.00002207263,0.0001299658,0.0001511694,0.00007684966,0.9845604,0.005602178,0.002224812,0.001005586,0.00002031476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3998502,0.00335437,0.5867357,0.000988577,0.0005872251,0.0002156334,0.001337735,0.003502603,0.00342796],"genre_scores_gemma":[0.8581151,0.0004742657,0.1353476,0.0004186064,0.0002626956,0.0001066128,0.003042416,0.000103845,0.00212881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002947544,"threshold_uncertainty_score":0.008915007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01008726910100979,"score_gpt":0.2993627430291062,"score_spread":0.2892754739280964,"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."}}