{"id":"W4200477224","doi":"10.1109/embc46164.2021.9629763","title":"Ocular Diseases Detection using Recent Deep Learning Techniques","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Computer science; Blindness; Fundus (uterus); Artificial intelligence; Disease; Machine learning; Medicine; Optometry; Ophthalmology; Pathology","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":[0.0003533008,0.0001932517,0.0004281149,0.0001579776,0.00006210979,0.00001326996,0.0002174718,0.0001422803,0.0002661983],"category_scores_gemma":[0.0009986978,0.0001466737,0.0002489146,0.0005867283,0.0002079061,0.00007439526,0.00009329731,0.0005674451,0.000002702596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001433836,"about_ca_system_score_gemma":0.00009111351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001918313,"about_ca_topic_score_gemma":0.00003675901,"domain_scores_codex":[0.9986739,0.0001012873,0.0004188247,0.000317404,0.0002664036,0.0002221454],"domain_scores_gemma":[0.9986755,0.000119841,0.0001623065,0.0002418235,0.0007257086,0.00007478992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006472179,0.0001693363,0.09435087,0.0001640712,0.0007574437,0.00001681997,0.001409239,0.005706759,0.8847857,0.0001579841,0.0004681231,0.01194899],"study_design_scores_gemma":[0.005470247,0.0008006006,0.07203224,0.007641839,0.002192627,0.0008985067,0.009727754,0.4992205,0.200056,0.001137195,0.199,0.001822471],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9206334,0.001515342,0.07159325,0.004380372,0.001172596,0.0001771718,0.00001923407,0.0001047776,0.0004038492],"genre_scores_gemma":[0.9883208,0.003177264,0.006837933,0.0002429502,0.0005468639,0.00001274653,0.00010188,0.00002193788,0.0007375804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6847296,"threshold_uncertainty_score":0.5981179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03466534288842317,"score_gpt":0.3285425136023275,"score_spread":0.2938771707139043,"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."}}