{"id":"W4404809464","doi":"10.1109/tcsvt.2024.3508470","title":"A Reference-Free Quality Enhancement Framework for Low-Quality Fundus Images","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Department of Science and Technology of Liaoning Province; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Quality (philosophy); Image quality; Computer vision; Artificial intelligence; Fundus (uterus); Image (mathematics); Physics","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":[0.000784054,0.0002378096,0.0006653477,0.0004851033,0.0002479043,0.0001040063,0.000156913,0.0003331284,0.00002303794],"category_scores_gemma":[0.0001477377,0.000196129,0.0002561321,0.0004527003,0.0001756554,0.00007790651,0.000002398502,0.000445018,0.00001350897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112536,"about_ca_system_score_gemma":0.00008748985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001656259,"about_ca_topic_score_gemma":0.00001786478,"domain_scores_codex":[0.9980609,0.000059061,0.0006516907,0.0006294775,0.0002242574,0.00037466],"domain_scores_gemma":[0.9983224,0.0005799495,0.0001134962,0.0006560158,0.0002208138,0.0001073375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006700603,0.001352342,0.0004381309,0.01855892,0.003407707,0.00005990244,0.0007481111,0.0001281137,0.1617302,0.1695643,0.005784931,0.6375573],"study_design_scores_gemma":[0.01362256,0.01022377,0.0008441624,0.01941489,0.006831808,0.001007688,0.01144593,0.01882374,0.4891078,0.1865901,0.2379851,0.004102545],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05173115,0.003382791,0.9379693,0.004079512,0.0007110308,0.001041285,0.000374212,0.0004619004,0.0002488348],"genre_scores_gemma":[0.9950767,0.0003766205,0.001087262,0.0001406137,0.00010627,0.0009686776,0.00001189063,0.00003523552,0.002196798],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9433455,"threshold_uncertainty_score":0.7997906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07036308052212395,"score_gpt":0.3778315365460834,"score_spread":0.3074684560239594,"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."}}