{"id":"W1173307404","doi":"","title":"Enhacing Fundus Retinal Images Through Polarization and Overall Image Quality Metrics","year":2007,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fundus (uterus); Image quality; Retinal; Computer science; Ophthalmology; Fundus camera; Optometry; Artificial intelligence; Computer vision; Image (mathematics); Medicine; Ophthalmoscopy","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.003131175,0.0002175147,0.0003944122,0.0003675238,0.0004655272,0.00009918264,0.0001799082,0.0001008811,0.00005899333],"category_scores_gemma":[0.003907833,0.0001857635,0.0000713897,0.002033711,0.005009268,0.0006866998,0.0001645324,0.0003836747,0.000021101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001409586,"about_ca_system_score_gemma":0.0002190565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007015724,"about_ca_topic_score_gemma":0.000001266596,"domain_scores_codex":[0.9974719,0.0001752193,0.000449573,0.0006979158,0.0006352828,0.0005701521],"domain_scores_gemma":[0.9982882,0.0003575735,0.0002587081,0.0002311144,0.0005003224,0.0003641524],"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":[0.00003435325,0.00005558576,0.2893997,0.00002291092,0.00001556149,0.0001857934,0.0004915665,4.343585e-7,0.7091838,0.0002953778,0.00001400443,0.0003008556],"study_design_scores_gemma":[0.000292912,0.0003265438,0.5663328,0.000051393,0.00006039277,0.0005910613,0.0004984693,0.0001654185,0.4286728,0.002824255,0.00001939086,0.0001645669],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897254,0.000200038,0.001031082,0.001078919,0.00008799779,0.0001501128,0.000004230943,0.00005240437,0.007669846],"genre_scores_gemma":[0.9757066,0.000008444281,0.02298824,0.0005829203,0.00008656923,0.000002709895,0.00001002698,0.00001284547,0.0006016569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2805111,"threshold_uncertainty_score":0.9976985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06059027985321035,"score_gpt":0.4099214802878622,"score_spread":0.3493312004346519,"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."}}