{"id":"W4411783711","doi":"10.18280/ts.420337","title":"Feature Convergence for Diabetic Retinopathy Detection Based on Activated Convolution Networks Using Fundus Images","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Fundus (uterus); Convolution (computer science); Convergence (economics); Diabetic retinopathy; Computer science; Feature (linguistics); Artificial intelligence; Retinopathy; Pattern recognition (psychology); Computer vision; Ophthalmology; Medicine; Diabetes mellitus; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006026777,0.0005285235,0.0004291667,0.0007802504,0.0002710145,0.0004759055,0.0006341964,0.0005056327,0.001091546],"category_scores_gemma":[0.001723486,0.0002539415,0.0005222841,0.0004750217,0.0002746761,0.0005812401,0.0005212402,0.0005685393,0.0002518535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000613704,"about_ca_system_score_gemma":0.0005422407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004947157,"about_ca_topic_score_gemma":0.003778969,"domain_scores_codex":[0.9997154,0.00004374785,0.00001637575,0.00007678588,0.00009875943,0.00004890896],"domain_scores_gemma":[0.999552,0.0001520685,0.00005237164,0.00004023197,0.0001779735,0.00002523438],"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":[0.0007634031,0.0002168347,0.005596149,0.0001168597,0.0001381802,0.0002935355,0.0001738248,0.2262581,0.08065885,0.004030006,0.002129626,0.6796247],"study_design_scores_gemma":[0.000004383917,0.00004526342,0.001069971,0.000004694773,0.00001143211,0.00006112022,0.000007719377,0.9883906,0.009564819,0.0006070794,0.0002263989,0.000006617282],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1435497,0.000380754,0.8526778,0.0001587703,0.00005035363,0.00005994263,0.00008792815,0.001286835,0.001747839],"genre_scores_gemma":[0.824001,0.0002045214,0.1730209,0.00007466552,0.0000289927,0.00006217429,0.0001948745,0.00005189914,0.002360976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004947157,"threshold_uncertainty_score":0.009836733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01442028866771656,"score_gpt":0.2746898487316605,"score_spread":0.260269560063944,"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."}}