{"id":"W2750841333","doi":"10.1155/2017/4826385","title":"An Automatic Image Processing System for Glaucoma Screening","year":2017,"lang":"en","type":"article","venue":"International Journal of Biomedical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Glaucoma; Thresholding; Fundus (uterus); Computer science; Artificial intelligence; Optic disc; Optic nerve; Segmentation; Inpainting; Image processing; Optic cup (embryology); Computer vision; Population; Optometry; Ophthalmology; Medicine; 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":[],"consensus_categories":[],"category_scores_codex":[0.0009390571,0.0001305868,0.0003541754,0.0003800892,0.0002497569,0.0005704823,0.0006642667,0.00003548392,0.00002592943],"category_scores_gemma":[0.0006280119,0.00009978381,0.0002679066,0.00005464916,0.0002606155,0.0008130095,0.00005564862,0.000218989,0.000004405364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001125735,"about_ca_system_score_gemma":0.0001483317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000273016,"about_ca_topic_score_gemma":3.490221e-7,"domain_scores_codex":[0.9980849,0.00003072853,0.000633894,0.0001687863,0.0008718185,0.0002098483],"domain_scores_gemma":[0.9974585,0.00006023756,0.0008752012,0.000228393,0.001085728,0.0002919153],"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":[0.0002300129,0.0002728333,0.05586355,0.0002774924,0.0004410566,0.001602392,0.0002280373,0.000001154408,0.0732101,0.00005231963,0.0010743,0.8667467],"study_design_scores_gemma":[0.007143187,0.0003559511,0.09184905,0.007201762,0.0009289773,0.01070309,0.002108603,0.8644913,0.007819879,0.0002794482,0.006743746,0.0003749634],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3900418,0.000270811,0.5872148,0.02050739,0.001031244,0.000129526,0.00001306397,0.00007806503,0.000713244],"genre_scores_gemma":[0.9188149,0.00000615597,0.0793663,0.0002465287,0.001477162,0.000002746234,0.00001434051,0.00002122736,0.00005066533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8663718,"threshold_uncertainty_score":0.5501174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01655566465361247,"score_gpt":0.367888275393517,"score_spread":0.3513326107399046,"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."}}