{"id":"W3095850453","doi":"10.3934/mbe.2020394","title":"Retinal blood vessel segmentation from fundus image using an efficient multiscale directional representation technique Bendlets","year":2020,"lang":"en","type":"article","venue":"Mathematical Biosciences & Engineering","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Fundus (uterus); Computer vision; Robustness (evolution); Hypertensive retinopathy; Retinal; Macular degeneration; Diabetic retinopathy; Biometrics; Benchmark (surveying); Image segmentation; Blood vessel; Pattern recognition (psychology); Feature (linguistics); Ophthalmology; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0002074921,0.0001467245,0.0002400466,0.000100764,0.00009986825,0.0000928156,0.0001053951,0.0000477283,0.0001184555],"category_scores_gemma":[0.0003103092,0.0001252512,0.0000858807,0.0005265279,0.00008704854,0.0001658426,0.00003944373,0.0001564199,0.00001589755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003694968,"about_ca_system_score_gemma":0.00002373574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004115813,"about_ca_topic_score_gemma":2.011994e-7,"domain_scores_codex":[0.9986078,0.00002845645,0.0003018128,0.0003872888,0.0004594424,0.0002152709],"domain_scores_gemma":[0.9994054,0.0000843642,0.00007185818,0.000149316,0.00006063815,0.0002284085],"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":[0.00001003384,0.0001619743,0.0007894313,0.00004418887,0.00002079632,0.0000241298,0.0004085696,0.004111386,0.9941216,0.0000693706,0.000006530798,0.0002319784],"study_design_scores_gemma":[0.000201002,0.00007511823,0.001136392,0.0001178656,0.0001402594,0.00004507667,0.0002808971,0.6181673,0.3796571,0.0000524364,0.000008845468,0.0001176728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5800148,0.00002386217,0.4191419,0.0003973423,0.00003354141,0.0001530455,0.000005582972,0.0001239814,0.0001058678],"genre_scores_gemma":[0.7610541,0.000002536699,0.238712,0.00005214399,0.0001218402,0.00001530106,0.00001904297,0.0000125897,0.0000104212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6144645,"threshold_uncertainty_score":0.5107594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03405069757194815,"score_gpt":0.3031677779789423,"score_spread":0.2691170804069942,"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."}}