{"id":"W4220769684","doi":"10.1002/ima.22720","title":"A deep data‐driven approach for enhanced segmentation of blood vessel for diabetic retinopathy","year":2022,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Preprocessor; Deep learning; Pattern recognition (psychology); Artificial neural network; Tree (set theory); Process (computing); Image segmentation; Feature (linguistics); Computer vision; Mathematics","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":[0.0004666804,0.00007550728,0.0003004842,0.0005046927,0.00005886767,0.00002148953,0.0003006489,0.0000234239,0.00000281288],"category_scores_gemma":[0.0001994113,0.00006640802,0.00007071615,0.0001387481,0.00006765245,0.00008566709,0.0001014865,0.0001339519,5.483885e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003616702,"about_ca_system_score_gemma":0.00005342974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000110797,"about_ca_topic_score_gemma":1.481634e-7,"domain_scores_codex":[0.9989843,0.00002537321,0.0004713653,0.0001615178,0.0002551566,0.0001022927],"domain_scores_gemma":[0.9985477,0.00007352918,0.0005820545,0.0001507576,0.0006177764,0.00002815456],"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":[0.0009296691,0.001208198,0.0619256,0.0009759095,0.003647296,0.0001066296,0.000811148,0.002700768,0.8666396,0.003588606,0.001510798,0.05595582],"study_design_scores_gemma":[0.01697711,0.002373643,0.0007832852,0.0008305923,0.003544553,0.008899929,0.01649524,0.868314,0.0737967,0.002155049,0.005360209,0.0004696838],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4978152,0.003958934,0.4925084,0.004388167,0.0006036484,0.0004976044,0.0001076656,0.00002861973,0.00009179847],"genre_scores_gemma":[0.9782246,0.00004817389,0.02135061,0.0000397451,0.0001292593,0.00005064684,0.00008416165,0.00001215781,0.00006067245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8656132,"threshold_uncertainty_score":0.270804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01357573330809134,"score_gpt":0.2945823083601834,"score_spread":0.281006575052092,"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."}}