{"id":"W2414079435","doi":"10.1016/j.compmedimag.2016.06.001","title":"A multi-scale tensor voting approach for small retinal vessel segmentation in high resolution fundus images","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Fundus (uterus); Computer vision; Segmentation; Computer science; Pixel; Sensitivity (control systems); Diabetic retinopathy; Pattern recognition (psychology); Line (geometry); Image segmentation; False positive rate; Mathematics; 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":[0.001141079,0.000202054,0.0004292285,0.0003037141,0.0001327544,0.00005241492,0.0001072738,0.00009882249,0.000005656897],"category_scores_gemma":[0.0004900436,0.0001403076,0.0001271599,0.0003116576,0.0003384743,0.00009960807,0.00006888714,0.0002604853,0.000001078176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003818754,"about_ca_system_score_gemma":0.00005925539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009507797,"about_ca_topic_score_gemma":0.000003362568,"domain_scores_codex":[0.9981998,0.0001462697,0.0004344428,0.0005039372,0.0003263378,0.0003891939],"domain_scores_gemma":[0.9989507,0.0003123206,0.0001241458,0.0001749509,0.0001529047,0.0002849636],"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":[0.001379001,0.001234342,0.4428312,0.001165308,0.0002258966,0.0002710051,0.0006056242,0.00001429812,0.1375328,0.0003068924,0.002695236,0.4117384],"study_design_scores_gemma":[0.01522013,0.0001792495,0.1435583,0.001873437,0.0003175408,0.0004104046,0.0003015483,0.8350648,0.001672847,0.000201914,0.0007290867,0.000470746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1828603,0.0004633293,0.807969,0.008207071,0.0001011686,0.0002682993,0.000009914506,0.00009930173,0.00002161097],"genre_scores_gemma":[0.7045829,0.0003961165,0.293342,0.001054729,0.0002821732,0.00005362617,0.00008643567,0.00003097098,0.0001710382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8350505,"threshold_uncertainty_score":0.572158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0253056685054254,"score_gpt":0.2891488587720105,"score_spread":0.2638431902665851,"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."}}