{"id":"W2884292375","doi":"10.1109/tmi.2018.2854886","title":"Supervised Segmentation of Un-Annotated Retinal Fundus Images by Synthesis","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Chinese Government Scholarship; China Scholarship Council","keywords":"Computer science; Pipeline (software); Fundus (uterus); Artificial intelligence; Segmentation; Data set; Set (abstract data type); Image segmentation; Focus (optics); Pattern recognition (psychology); Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009887886,0.0007635,0.0007438627,0.0009368155,0.0002477393,0.0009751846,0.0007690159,0.0008580127,0.0009252588],"category_scores_gemma":[0.002319854,0.0003839398,0.0005380823,0.0006804324,0.0006468531,0.0007729838,0.0007187154,0.0005972329,0.000460141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00047976,"about_ca_system_score_gemma":0.0007343773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452087,"about_ca_topic_score_gemma":0.002734992,"domain_scores_codex":[0.999411,0.0001344604,0.00004031512,0.0002213867,0.0001329696,0.00005993169],"domain_scores_gemma":[0.9988914,0.0003524082,0.0001759745,0.0003291763,0.0002028282,0.00004824613],"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":[0.001321795,0.0002475031,0.0046501,0.0006157426,0.0001828993,0.0007364294,0.000543988,0.1457992,0.4381809,0.004983584,0.003320239,0.3994176],"study_design_scores_gemma":[0.00002943046,0.0002663847,0.003879472,0.00003342034,0.00005818513,0.000717726,0.0001351126,0.8428406,0.1442217,0.003294491,0.00448847,0.00003506947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2521477,0.0008800116,0.7414829,0.0002811849,0.00007670632,0.0001634042,0.0006025657,0.001957264,0.002408346],"genre_scores_gemma":[0.5589235,0.0004727059,0.4365134,0.0001672105,0.00008090152,0.0001219024,0.001674947,0.000257645,0.001787717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001452087,"threshold_uncertainty_score":0.005229235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01158039288741047,"score_gpt":0.2896817830643729,"score_spread":0.2781013901769624,"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."}}