{"id":"W3215526847","doi":"10.1038/s41597-022-01507-y","title":"The RETA Benchmark for Retinal Vascular Tree Analysis","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; Capital Medical University","keywords":"Segmentation; Annotation; Computer science; Benchmark (surveying); Tree (set theory); Artificial intelligence; Workflow; Software; Visualization; Task (project management); Pattern recognition (psychology); Database","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":[0.004853001,0.00258772,0.001182147,0.00596047,0.0011983,0.003542687,0.003297495,0.00252232,0.003484226],"category_scores_gemma":[0.01209856,0.0007103271,0.002164161,0.002952158,0.0007318865,0.001374608,0.002245764,0.001520473,0.00227899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113498,"about_ca_system_score_gemma":0.001319114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007628964,"about_ca_topic_score_gemma":0.009547159,"domain_scores_codex":[0.9964808,0.0009082049,0.0004384941,0.001012848,0.0009080092,0.0002517159],"domain_scores_gemma":[0.9948716,0.002031876,0.000441941,0.001238159,0.001098609,0.0003178643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003192322,0.001216936,0.0236967,0.004743558,0.00222333,0.001969896,0.0009513241,0.1879073,0.08063393,0.0109825,0.1879632,0.4945189],"study_design_scores_gemma":[0.0003589076,0.0009925443,0.02808087,0.0004369232,0.0004556004,0.003597647,0.0004118013,0.7794384,0.08633775,0.01434476,0.0852759,0.0002689343],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.3510357,0.01088111,0.3984558,0.001326459,0.001276694,0.001668439,0.06488731,0.1489141,0.02155434],"genre_scores_gemma":[0.4180595,0.001499476,0.4443416,0.0005125117,0.0002331622,0.001095809,0.1156738,0.01226439,0.006319734],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.007628964,"threshold_uncertainty_score":0.0256654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04504438264298648,"score_gpt":0.3250821636395643,"score_spread":0.2800377809965778,"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."}}