{"id":"W4403243140","doi":"10.1016/j.media.2024.103365","title":"RFMiD: Retinal Image Analysis for multi-Disease Detection challenge","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Diabetic retinopathy; Disease; Macular degeneration; Glaucoma; Central retinal artery occlusion; Preprocessor; Medicine; Fundus (uterus); Contextual image classification; Optometry; Retinal; Ophthalmology; Pattern recognition (psychology); Pathology; Image (mathematics); Diabetes mellitus","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00155965,0.0004342221,0.001326785,0.002720863,0.0002368935,0.0002764348,0.0002897014,0.0002043805,0.003291203],"category_scores_gemma":[0.001952583,0.000348871,0.003721668,0.007226367,0.0003573555,0.0002812777,0.00008962195,0.0006123173,0.0002463009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611894,"about_ca_system_score_gemma":0.00021338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000321027,"about_ca_topic_score_gemma":0.0002439069,"domain_scores_codex":[0.9956204,0.0001841861,0.0008719262,0.001217307,0.0014347,0.0006714945],"domain_scores_gemma":[0.9969702,0.000298013,0.0001381644,0.0008395766,0.00048688,0.001267169],"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":[0.00323686,0.006817795,0.108529,0.007179874,0.3532957,0.02427292,0.002654287,0.0005102919,0.03968795,0.0004129237,0.01593151,0.4374709],"study_design_scores_gemma":[0.0008807144,0.0001309559,0.01327476,0.0001391197,0.1206493,0.00001995739,0.0002301952,0.8572274,0.0009308518,0.00007328376,0.006032576,0.0004108093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03826761,0.004053201,0.942795,0.01282991,0.0001451296,0.0003489917,0.00009536137,0.0005470679,0.0009176758],"genre_scores_gemma":[0.9785464,0.0007734106,0.01332269,0.0006622438,0.000714213,0.0001518627,0.000698069,0.00007140079,0.005059673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9402788,"threshold_uncertainty_score":0.9998963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02624280849333781,"score_gpt":0.3576893885822046,"score_spread":0.3314465800888668,"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."}}