{"id":"W3125010089","doi":"10.18280/ria.340602","title":"A Novel Filtered Segmentation-Based Bayesian Deep Neural Network Framework on Large Diabetic Retinopathy Databases","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Thresholding; Segmentation; Pattern recognition (psychology); Artificial neural network; Image segmentation; Bayesian probability; Deep learning; Feature (linguistics); Outlier; Image (mathematics)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000254374,0.0002571985,0.0004157162,0.00008425289,0.000207087,0.00006340234,0.0001978824,0.00006408538,0.001002586],"category_scores_gemma":[0.0009142341,0.000237133,0.0002296168,0.0008581713,0.00008394519,0.00007256964,0.00005050282,0.0004351571,0.0003833935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003951534,"about_ca_system_score_gemma":0.00003816965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001763413,"about_ca_topic_score_gemma":0.000003924432,"domain_scores_codex":[0.9979851,0.00007939085,0.0005196956,0.0005978871,0.0003055662,0.0005123622],"domain_scores_gemma":[0.9984027,0.0004955306,0.0001601911,0.000561644,0.0001041118,0.000275785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001460101,0.002375842,0.08182188,0.001176481,0.000334927,0.0006343396,0.00479893,0.7919757,0.05353057,0.004205683,0.006137393,0.05154809],"study_design_scores_gemma":[0.0001343742,0.0003730994,0.0003231776,0.0005240063,0.0001641424,0.00001204945,0.0007200796,0.9659111,0.03042257,0.00008238974,0.00108176,0.0002512879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06616953,0.0003271256,0.9208841,0.01127996,0.0002040127,0.0003704106,0.00004339241,0.0001651066,0.0005563929],"genre_scores_gemma":[0.9702157,0.0000224435,0.02078989,0.008022286,0.000518742,0.00002944302,0.0001733305,0.00004200128,0.0001861962],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9040461,"threshold_uncertainty_score":0.9999107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05235270270858598,"score_gpt":0.30902529335348,"score_spread":0.256672590644894,"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."}}