{"id":"W4308748502","doi":"10.1016/j.compbiomed.2022.106283","title":"Asynchronous feature regularization and cross-modal distillation for OCT based glaucoma diagnosis","year":2022,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Optical coherence tomography; Glaucoma; Computer science; Artificial intelligence; Machine learning; Deep learning; Feature (linguistics); Regularization (linguistics); Asynchronous communication; Medicine; Ophthalmology","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":[0.0009661484,0.0005069572,0.0004975881,0.0005090864,0.0003637509,0.0006952821,0.0007464009,0.0008548053,0.001662573],"category_scores_gemma":[0.002464397,0.0002911038,0.0006579774,0.0004357766,0.0004313522,0.0009743112,0.001056676,0.001131774,0.000407679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003657131,"about_ca_system_score_gemma":0.0009208245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003153138,"about_ca_topic_score_gemma":0.004695635,"domain_scores_codex":[0.9996802,0.000107876,0.00001803056,0.00005776006,0.0000970311,0.00003926495],"domain_scores_gemma":[0.9992829,0.0003896573,0.00005755947,0.00007562897,0.000157431,0.00003679996],"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":[0.001261537,0.0003946452,0.00311076,0.0003007908,0.0001700664,0.0002133787,0.000171883,0.2486995,0.08602803,0.02643763,0.006728329,0.6264833],"study_design_scores_gemma":[0.00001192031,0.00003732481,0.0005112512,0.000007380188,0.00001519156,0.00005097971,0.000007588008,0.9894002,0.006285646,0.002968963,0.0006916585,0.00001186739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0299329,0.0004704249,0.9671296,0.0003880629,0.00007082758,0.00004196756,0.0001613153,0.0005563896,0.001248456],"genre_scores_gemma":[0.5189008,0.0005205296,0.4742941,0.0003108307,0.0001599519,0.0001272665,0.0005366659,0.0001484115,0.005001422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003153138,"threshold_uncertainty_score":0.006269574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009336418573978105,"score_gpt":0.3027319899318117,"score_spread":0.2933955713578336,"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."}}