{"id":"W2997616821","doi":"","title":"Generative Modeling for Retinal Fundus Image Synthesis","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Fundus (uterus); Generative grammar; Image (mathematics); Annotation; Generative adversarial network; Generative model; Deep learning; Residual; Encoder; Pattern recognition (psychology); Computer vision; Algorithm; Medicine; Ophthalmology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000737149,0.0001207812,0.0004303647,0.0002511411,0.00008301586,0.0001447397,0.00005543477,0.00002409131,0.00001590739],"category_scores_gemma":[0.0001537226,0.0000870194,0.0001881132,0.0001015349,0.0000323434,0.0002317661,0.00001470322,0.0001400745,0.000008178542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004787367,"about_ca_system_score_gemma":0.00009337922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008813316,"about_ca_topic_score_gemma":4.12816e-8,"domain_scores_codex":[0.9987382,0.00006880461,0.0005385041,0.0001328453,0.0003925477,0.0001291558],"domain_scores_gemma":[0.9982919,0.0002979553,0.0003223495,0.00007361105,0.0008972241,0.0001169971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003099637,0.0007773167,0.1189447,0.002820983,0.001784523,0.0002483578,0.00230133,0.671304,0.1111078,0.003293076,0.02069803,0.0636202],"study_design_scores_gemma":[0.0009411027,0.0001625986,0.001699552,0.0007903663,0.0001691883,0.001213889,0.000803826,0.992793,0.00008206526,0.0004607567,0.000783591,0.0001000126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5678003,0.001524434,0.4268163,0.002792299,0.0003136875,0.000202576,0.000006606436,0.00001636636,0.0005274374],"genre_scores_gemma":[0.9775217,0.00003032128,0.02162153,0.0001764993,0.0003042098,0.000002644009,0.000005703367,0.00001594019,0.0003215058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4097214,"threshold_uncertainty_score":0.3548548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01550385286363505,"score_gpt":0.3135633875603596,"score_spread":0.2980595346967245,"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."}}