{"id":"W2888163428","doi":"10.1016/j.compmedimag.2018.08.008","title":"Efficient multi-kernel multi-instance learning using weakly supervised and imbalanced data for diabetic retinopathy diagnosis","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; False positive paradox; Computer science; Diabetic retinopathy; Machine learning; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Kernel (algebra); Medicine; Diabetes mellitus; Mathematics","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":[0.002722211,0.001183506,0.002688741,0.001359513,0.000639228,0.001559944,0.003276488,0.00223767,0.001054261],"category_scores_gemma":[0.006071805,0.0006751402,0.001811084,0.001147977,0.0005169784,0.001899839,0.002190328,0.002375996,0.0008014388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007414724,"about_ca_system_score_gemma":0.001281454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005123085,"about_ca_topic_score_gemma":0.004561729,"domain_scores_codex":[0.9983601,0.0005324888,0.0001464716,0.000463801,0.0002772124,0.0002199629],"domain_scores_gemma":[0.9973831,0.001253957,0.0002166402,0.0004394276,0.0005208603,0.0001860253],"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":[0.002004171,0.001148761,0.01192468,0.0003934392,0.0005718554,0.0002766035,0.000163077,0.2840158,0.01157274,0.002415771,0.01291251,0.6726006],"study_design_scores_gemma":[0.00001180405,0.00003363965,0.0004436436,0.000005177136,0.00002350068,0.00002835965,0.00001512936,0.9972882,0.0009846818,0.0009481254,0.0002119188,0.000005715003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1297279,0.002731026,0.8610461,0.0007179945,0.0002330109,0.0001280271,0.000974345,0.003567545,0.0008742114],"genre_scores_gemma":[0.8082777,0.0004085771,0.1848413,0.000258385,0.000179448,0.000140799,0.003749665,0.0002013014,0.001943008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005123085,"threshold_uncertainty_score":0.01439655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04435630286224258,"score_gpt":0.3339190018480665,"score_spread":0.2895626989858239,"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."}}