{"id":"W3172614365","doi":"10.1109/tmi.2021.3090082","title":"Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":437,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Canadian VIGOUR Centre; University of Alberta","funders":"Engineering and Physical Sciences Research Council; European Commission; Nvidia","keywords":"Generalizability theory; Benchmarking; Deep learning; Scanner; Segmentation; Cardiac magnetic resonance; Cardiac imaging; Homogeneous; Image segmentation","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.008944499,0.002238166,0.002629168,0.001910347,0.001202643,0.002349006,0.002360125,0.006160309,0.00125285],"category_scores_gemma":[0.01348057,0.0008657851,0.001873899,0.002233027,0.00165282,0.001530899,0.002558883,0.002377579,0.001118383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408523,"about_ca_system_score_gemma":0.002428556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007286083,"about_ca_topic_score_gemma":0.01167751,"domain_scores_codex":[0.9945504,0.001893765,0.0003584783,0.001777185,0.001001691,0.0004183656],"domain_scores_gemma":[0.9891139,0.005677546,0.0007380167,0.002093387,0.001187591,0.001189511],"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":[0.003343546,0.001110534,0.03415206,0.00320726,0.001752427,0.004540977,0.001421392,0.1607252,0.0260044,0.006910102,0.2039108,0.5529214],"study_design_scores_gemma":[0.0006935392,0.001037157,0.05334511,0.0006066115,0.0008437361,0.01258373,0.00239357,0.7179847,0.04738407,0.04427816,0.1184006,0.0004490473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5951456,0.02588055,0.3046087,0.02908593,0.003747481,0.0008024491,0.02219122,0.009403428,0.00913456],"genre_scores_gemma":[0.7134232,0.003571518,0.2332771,0.004339432,0.002150083,0.0003627732,0.03543242,0.001738918,0.005704592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008944499,"threshold_uncertainty_score":0.04730356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02988244004054808,"score_gpt":0.3157475722390445,"score_spread":0.2858651321984964,"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."}}