{"id":"W4385287027","doi":"10.1016/j.bspc.2023.105289","title":"FundusGAN: Fundus image synthesis based on semi-supervised learning","year":2023,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; National Research Foundation of Korea; Information Technology Research Centre; Ministry of Science, ICT and Future Planning","keywords":"Fundus (uterus); Computer science; Artificial intelligence; Diabetic retinopathy; Matching (statistics); Image (mathematics); Pattern recognition (psychology); Feature (linguistics); Construct (python library); Computer vision; Medicine; Ophthalmology; Pathology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.000674709,0.0002212959,0.0004746054,0.0003285378,0.0003239883,0.0001269719,0.00008913349,0.0001427588,0.0002691517],"category_scores_gemma":[0.0004991133,0.0001629667,0.0001467336,0.0007729629,0.0002792894,0.00006312197,0.00001930701,0.0004312143,0.0001309052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003189132,"about_ca_system_score_gemma":0.0001438427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002297565,"about_ca_topic_score_gemma":1.723778e-7,"domain_scores_codex":[0.9980639,0.0001205952,0.0002984161,0.0004352338,0.0006318901,0.0004499633],"domain_scores_gemma":[0.9987901,0.0004652264,0.0000824766,0.0001287272,0.0001015364,0.0004319006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000977793,0.000334571,0.007932054,0.000667655,0.0001657678,0.000596553,0.0001381708,0.00006341987,0.1247184,0.000007224844,0.001889009,0.8625094],"study_design_scores_gemma":[0.003327928,0.0005644012,0.004238122,0.001123551,0.0005657075,0.00003639167,0.0003985777,0.9793235,0.001359874,0.00006278989,0.008671067,0.0003281088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7094951,0.00371083,0.1418292,0.1216909,0.0002870289,0.001162588,0.00007200197,0.004089427,0.01766292],"genre_scores_gemma":[0.9968014,0.00002464858,0.0002214463,0.001450802,0.0003423454,0.00003895775,0.00003257125,0.00003300861,0.00105482],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9792601,"threshold_uncertainty_score":0.6645589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398309824164959,"score_gpt":0.2661057980282669,"score_spread":0.2521226997866174,"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."}}