{"id":"W4399164856","doi":"10.1016/j.bspc.2024.106489","title":"AugPaste: A one-shot approach for diabetic retinopathy detection","year":2024,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Shot (pellet); Diabetic retinopathy; Computer science; Retinopathy; Artificial intelligence; Medicine; Diabetes mellitus; Chemistry; Endocrinology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004585729,0.0008732475,0.0009413711,0.001099016,0.0003822445,0.0008663851,0.0008816192,0.001111276,0.003383941],"category_scores_gemma":[0.0007156463,0.0003290485,0.0006630427,0.0004877457,0.000224985,0.0005915251,0.001201877,0.0008078534,0.001383474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002112922,"about_ca_system_score_gemma":0.0007218193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001946211,"about_ca_topic_score_gemma":0.004877426,"domain_scores_codex":[0.9996923,0.00006290097,0.00000783239,0.00006341154,0.0001313086,0.00004214217],"domain_scores_gemma":[0.9997759,0.00006016871,0.00001285264,0.00002814076,0.00008665096,0.00003622267],"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":[0.001294746,0.0003539548,0.001867794,0.0002291015,0.0002033518,0.0002803575,0.00009940535,0.0145715,0.1439896,0.003178999,0.009655605,0.8242756],"study_design_scores_gemma":[0.00006991927,0.0004007886,0.003782865,0.00002882221,0.0001360308,0.0008340033,0.00006083886,0.9249241,0.05698062,0.004257414,0.008459172,0.00006532724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02232116,0.0005567509,0.971493,0.0002049746,0.0001486351,0.00009644908,0.0003588035,0.002661035,0.002159178],"genre_scores_gemma":[0.1734246,0.0006228224,0.8143743,0.0003646922,0.0001543216,0.0001314142,0.0009376397,0.0003331224,0.009657168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003383941,"threshold_uncertainty_score":0.01132041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02330300028195028,"score_gpt":0.280775548006603,"score_spread":0.2574725477246527,"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."}}