{"id":"W2035995330","doi":"10.1167/iovs.13-13310","title":"Automated Segmentation of Optic Nerve Head Structures With Optical Coherence Tomography","year":2014,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Advanced Scientific Computing Research; Canadian Institutes of Health Research; Heidelberg Engineering","keywords":"Interquartile range; Optical coherence tomography; Nuclear medicine; Optic nerve; Medicine; Segmentation; Image quality; Internal limiting membrane; Mathematics; Ophthalmology; Artificial intelligence; Computer science; Surgery; Visual acuity; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003660802,0.000191291,0.0003338944,0.0002282679,0.0001630094,0.00001986056,0.0002170634,0.00008953417,0.00005692273],"category_scores_gemma":[0.0003329827,0.0001312898,0.00005100195,0.001199445,0.007451762,0.0001654377,0.00006272403,0.0001871435,0.000009283458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003479901,"about_ca_system_score_gemma":0.0003103481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001189584,"about_ca_topic_score_gemma":0.000002807368,"domain_scores_codex":[0.9982628,0.0001175569,0.000272983,0.0004503015,0.0005178804,0.0003784565],"domain_scores_gemma":[0.9988871,0.0001296015,0.000167752,0.0001948843,0.000318008,0.0003026658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001088558,0.0001001583,0.2924808,0.00004277494,0.00002377735,0.00008734199,0.0003394972,0.00002261703,0.7054288,0.001215301,0.000009324913,0.0001407484],"study_design_scores_gemma":[0.0005712098,0.003295609,0.6771275,0.00009572848,0.00004551209,0.0008147513,0.0002989236,0.002434276,0.3135315,0.001661172,0.000001213632,0.0001226078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966412,0.00003184997,0.00002669641,0.0002753177,0.0000814142,0.0003624301,0.000001695005,0.00008371262,0.002495732],"genre_scores_gemma":[0.9864393,3.618139e-7,0.0133765,0.0001010439,0.00001734182,0.00001900367,0.000009150614,0.00001068401,0.00002658382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3918973,"threshold_uncertainty_score":0.9952494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02319400147501299,"score_gpt":0.3359270806362594,"score_spread":0.3127330791612464,"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."}}