{"id":"W4385388935","doi":"10.18280/ria.370307","title":"Automated Retinal Hard Exudate Detection Using Novel Rhombus Multilevel Segmentation Algorithm","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rhombus; Segmentation; Exudate; Computer science; Algorithm; Artificial intelligence; Pattern recognition (psychology); Retinal; Mathematics; Ophthalmology; Geometry; Biology; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004381001,0.000184927,0.0002771247,0.0003438797,0.000240645,0.00006681599,0.00009847861,0.00008161405,0.0001503412],"category_scores_gemma":[0.0001713554,0.0001809841,0.0001599914,0.001138653,0.00008442441,0.0001412738,0.00004596253,0.000206902,0.0007462522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215647,"about_ca_system_score_gemma":0.0000416729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001768089,"about_ca_topic_score_gemma":0.000002863576,"domain_scores_codex":[0.9984086,0.00004112464,0.0004774801,0.0004377225,0.000270296,0.0003648253],"domain_scores_gemma":[0.9991095,0.00007335531,0.0001527266,0.0003247508,0.0002117216,0.0001279688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005149336,0.0001481421,0.001373474,0.0001171298,0.00007986103,0.00006557852,0.0007738341,0.02739178,0.773159,0.00001159085,0.0001658344,0.1966623],"study_design_scores_gemma":[0.00008854333,0.0000648755,0.001035496,0.0001596096,0.0001078231,0.00013328,0.001023284,0.7387964,0.258114,0.00002887477,0.0003089701,0.000138889],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4539594,0.00004144233,0.5443368,0.0002918503,0.0002566794,0.0002134729,0.00001106783,0.0006978706,0.0001914654],"genre_scores_gemma":[0.9580649,0.00007636811,0.03792972,0.00009542989,0.0002011393,0.00001951702,0.0001007293,0.00004235344,0.003469875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7114046,"threshold_uncertainty_score":0.9591811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08231580467314423,"score_gpt":0.3465055655659365,"score_spread":0.2641897608927922,"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."}}