{"id":"W3211126657","doi":"10.32920/ryerson.14648760.v1","title":"Automatic detection and classification of diabetic retinopathy from retinal fundus images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Diabetic retinopathy; Adaptive histogram equalization; Artificial intelligence; Thresholding; Fundus (uterus); Computer science; Retinal; Support vector machine; Retinopathy; Ophthalmology; Blindness; Computer vision; Retina; Medicine; Pattern recognition (psychology); Histogram; Optometry; Diabetes mellitus; Histogram equalization; Image (mathematics); Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006712903,0.0003434375,0.0005441871,0.002043016,0.0002050587,0.0009168141,0.0004140863,0.0005845307,0.001108597],"category_scores_gemma":[0.001311424,0.0002360116,0.0004847881,0.0007012124,0.000158801,0.0003606648,0.0002687953,0.000321965,0.000839978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003650262,"about_ca_system_score_gemma":0.0003821997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002396971,"about_ca_topic_score_gemma":0.002280117,"domain_scores_codex":[0.9995592,0.00006779654,0.00003033608,0.00008846528,0.0001952405,0.00005878066],"domain_scores_gemma":[0.9995002,0.0001004492,0.00005263169,0.00004790899,0.0002764705,0.00002235245],"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":[0.0005317071,0.0002195471,0.009397539,0.0002716357,0.00009351123,0.0002552003,0.00008631533,0.009189858,0.1545725,0.0009101774,0.009306435,0.8151655],"study_design_scores_gemma":[0.00006267551,0.0003375196,0.08376438,0.0001265391,0.0001484148,0.001861421,0.0002476223,0.6682976,0.2299271,0.001516439,0.01361028,0.0001001093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4706558,0.005442951,0.5085596,0.0008061473,0.0004331909,0.0003334421,0.001420458,0.0059546,0.006393763],"genre_scores_gemma":[0.636066,0.003308512,0.3519849,0.0001291293,0.0001169464,0.0001143635,0.002437301,0.0001430673,0.005699834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002396971,"threshold_uncertainty_score":0.004766107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150200368979546,"score_gpt":0.2787597510299916,"score_spread":0.2572577473401961,"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."}}