{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0048411,0.00009522333,0.0002386572,0.0002506448,0.001834635,0.0002944301,0.001208178,0.00001326932,0.0003973149],"category_scores_gemma":[0.0005158148,0.00006456707,0.0003212068,0.002355669,0.0002581814,0.00007309042,0.0007572186,0.000169108,0.00002136827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004278302,"about_ca_system_score_gemma":0.0001148496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005113856,"about_ca_topic_score_gemma":0.00007150685,"domain_scores_codex":[0.9978059,0.0001081923,0.0002600224,0.0007542876,0.0007730893,0.0002985277],"domain_scores_gemma":[0.9962657,0.0001395631,0.0001039639,0.003267172,0.0001250462,0.00009854316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000181829,0.0002337723,0.0153369,0.00004962526,0.003243855,0.0000338696,0.0002834748,0.0001597211,0.002163326,0.000498673,0.8943957,0.08341926],"study_design_scores_gemma":[0.0003009534,0.00004663018,0.003752249,0.000005602304,0.003891964,0.000009306722,0.0006261028,0.07010417,0.00007053179,0.0002153492,0.9208815,0.0000957084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.599708,0.0317497,0.07662788,0.1560765,0.01429043,0.006829929,0.04186481,0.001091489,0.07176133],"genre_scores_gemma":[0.7932052,0.00007795159,0.006867442,0.000542708,0.000383034,0.0001447424,0.04984056,0.00004152839,0.1488968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1934972,"threshold_uncertainty_score":0.9994649,"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."}}