{"id":"W4386197697","doi":"10.1007/978-981-99-3734-9_36","title":"MEDNet-Based Imbalanced Cataract Detection Using Ophthalmic Images","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cataracts; Preprocessor; Blindness; Artificial intelligence; Computer science; Support vector machine; Optometry; Medicine; Ophthalmology","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":[0.0008501796,0.0008421796,0.0009263699,0.002095311,0.0003580951,0.001069147,0.0007257388,0.0008003676,0.003315059],"category_scores_gemma":[0.00152596,0.0003793816,0.0007767618,0.001209485,0.0002159187,0.000829745,0.0007918087,0.0005764873,0.001960195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005815745,"about_ca_system_score_gemma":0.0006859906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005716031,"about_ca_topic_score_gemma":0.01096023,"domain_scores_codex":[0.9996247,0.00004585003,0.0000219853,0.00008783107,0.0001462066,0.0000734819],"domain_scores_gemma":[0.9995853,0.0001327713,0.00003656998,0.00005267694,0.0001626174,0.00003001116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001109817,0.000296003,0.008191396,0.0001349295,0.0001888423,0.0002089128,0.00004013673,0.03402068,0.02497013,0.001335212,0.01719244,0.9123114],"study_design_scores_gemma":[0.00003536344,0.0001259182,0.007603895,0.00003400304,0.00008904886,0.0005103038,0.00004685622,0.9589542,0.02485043,0.002397856,0.005327058,0.00002515413],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2177214,0.00600875,0.7435989,0.001895854,0.001669178,0.0002806288,0.006181747,0.01007526,0.01256838],"genre_scores_gemma":[0.6543278,0.002502423,0.3175014,0.0005820746,0.0007798116,0.0001050871,0.0078902,0.0004346421,0.01587666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005716031,"threshold_uncertainty_score":0.01136553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02571411719486945,"score_gpt":0.2777093986374271,"score_spread":0.2519952814425576,"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."}}