{"id":"W3108591672","doi":"10.1002/mp.14676","title":"Toward data‐efficient learning: A benchmark for COVID‐19 CT lung and infection segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":251,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Segmentation; Medical imaging; Image segmentation; Deep learning; Computed tomography; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003746541,0.0001216869,0.0002285425,0.00002625313,0.0001135495,0.00002644005,0.00008759111,0.00005126072,0.0001102154],"category_scores_gemma":[0.004221368,0.0001120019,0.0000481,0.0002151106,0.00009459283,0.00006708065,0.00014596,0.000271797,0.00001029899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331872,"about_ca_system_score_gemma":0.0003973041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072841,"about_ca_topic_score_gemma":0.000002637617,"domain_scores_codex":[0.9986348,0.00004955274,0.0002034774,0.0004072296,0.0005219377,0.0001829774],"domain_scores_gemma":[0.9986185,0.0004870941,0.00007778953,0.00018453,0.00004871019,0.0005834205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008672624,0.001889387,0.1217452,0.008906915,0.0005148743,0.0002592242,0.01268009,0.00590551,0.002460168,0.0008820559,0.4665262,0.3773631],"study_design_scores_gemma":[0.006319785,0.000852994,0.004448629,0.0002667221,0.0005737735,0.00003597327,0.000192887,0.6482871,0.002321129,0.0002794923,0.336069,0.0003525389],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2119178,0.0002392353,0.6224907,0.1634466,0.0003254981,0.001175903,0.00003737303,0.0002802293,0.00008662452],"genre_scores_gemma":[0.9576906,0.00009863098,0.0004103138,0.04019534,0.0008393761,0.00004857625,0.0006742308,0.0000241531,0.00001877751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7457728,"threshold_uncertainty_score":0.5053676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08268855983109663,"score_gpt":0.3785273690815479,"score_spread":0.2958388092504513,"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."}}