{"id":"W4388441535","doi":"10.18280/isi.280526","title":"Enhanced Classification of Diabetic Retinopathy via Vessel Segmentation: A Deep Ensemble Learning Approach","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Diabetic retinopathy; Artificial intelligence; Ensemble learning; Segmentation; Deep learning; Computer science; Retinopathy; Diabetes mellitus; Pattern recognition (psychology); Machine learning; Medicine; Endocrinology","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":[0.0004801431,0.0001287319,0.0002731094,0.0004046714,0.0001540314,0.00005597539,0.00007111039,0.0000742668,0.00002337648],"category_scores_gemma":[0.0002956538,0.0001212775,0.00009642883,0.00107441,0.00009583309,0.0006907363,0.00002432963,0.0001478148,0.0001484377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001193143,"about_ca_system_score_gemma":0.00004550059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002068808,"about_ca_topic_score_gemma":3.465716e-7,"domain_scores_codex":[0.9986663,0.00007218128,0.0005837642,0.0001282571,0.0003385649,0.0002109275],"domain_scores_gemma":[0.9989573,0.0000520564,0.0003935146,0.0001922968,0.0003362434,0.00006855201],"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":[0.0002348283,0.0001315398,0.02428269,0.003359725,0.0002567069,0.000004644907,0.03530248,0.006375297,0.4444111,0.0004764202,0.0004507429,0.4847138],"study_design_scores_gemma":[0.001679391,0.000427951,0.1161021,0.000638685,0.0003879136,0.00006780618,0.01943105,0.6839256,0.1757036,0.0007841648,0.0004202065,0.0004316024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7202903,0.00004435899,0.2644653,0.0000715172,0.00006109651,0.0002378961,0.000001563862,0.0002045654,0.01462339],"genre_scores_gemma":[0.9960138,0.00005313788,0.002854976,0.00004284285,0.00004294708,0.00007318849,0.0005856549,0.00001306788,0.0003203592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6775503,"threshold_uncertainty_score":0.4945552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01722646620694719,"score_gpt":0.2589779269950394,"score_spread":0.2417514607880922,"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."}}