{"id":"W2155626145","doi":"10.1109/ssiai.2006.1633738","title":"Automated Retinal Vessel Segmentation Using Multiscale Analysis and Adaptive Thresholding","year":2006,"lang":"en","type":"article","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Hong Kong Polytechnic University","keywords":"Thresholding; Artificial intelligence; Computer vision; Segmentation; Computer science; Contrast (vision); Fundus (uterus); Retinal; Image segmentation; Pattern recognition (psychology); Image (mathematics); Ophthalmology","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":[0.0001293584,0.0001017331,0.0002487681,0.0002905034,0.00009746436,0.00003985799,0.00002098759,0.00003350545,0.0001454713],"category_scores_gemma":[0.00001134187,0.00008262641,0.0001016293,0.0007298722,0.00005495447,0.00009024407,0.00001624686,0.00006763073,0.000008997722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004422538,"about_ca_system_score_gemma":0.00001264166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001726909,"about_ca_topic_score_gemma":0.00002869318,"domain_scores_codex":[0.999225,0.00002831789,0.0001980249,0.0002246682,0.0001785012,0.000145538],"domain_scores_gemma":[0.9996605,0.00002731984,0.00007144463,0.0001057426,0.00007788857,0.00005713793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007938849,0.00009974675,0.7699063,0.00002425938,0.0007370074,0.00005654935,0.000121808,0.001060186,0.2256776,0.00004229553,0.0008828531,0.001312042],"study_design_scores_gemma":[0.0004431077,0.00003488842,0.2214154,0.00003361673,0.002515984,0.00002865595,0.0003883607,0.7589414,0.01606411,0.00002157234,0.00001392083,0.0000990376],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9489388,0.000100325,0.04692637,0.000204397,0.00001001556,0.00007283697,0.000002269956,0.0001978532,0.003547109],"genre_scores_gemma":[0.9454523,0.000008667734,0.05264999,0.00007064702,0.00004327931,0.000001888943,0.00004054472,0.000008775356,0.001723861],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7578812,"threshold_uncertainty_score":0.3369407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0191492083204794,"score_gpt":0.3087447830463476,"score_spread":0.2895955747258682,"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."}}