{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003285169,0.0002638275,0.0003615044,0.00009923967,0.0003447768,0.00007331902,0.00009016174,0.00007685339,0.0003899447],"category_scores_gemma":[0.0003868213,0.0002107196,0.0002996715,0.0002300553,0.0003145594,0.0001115806,0.000006866685,0.0006946122,0.0001179829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008726383,"about_ca_system_score_gemma":0.0003119661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008754339,"about_ca_topic_score_gemma":0.00005814105,"domain_scores_codex":[0.9978521,0.0001997627,0.0003344535,0.0005034656,0.000704163,0.0004060408],"domain_scores_gemma":[0.9979349,0.0005533482,0.00005112488,0.0004802516,0.0001931706,0.0007872353],"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":[0.0006705353,0.01342279,0.0504418,0.001325931,0.002027964,0.006043712,0.01096499,0.001335494,0.01255227,0.00005293293,0.01344638,0.8877152],"study_design_scores_gemma":[0.1058316,0.0002207275,0.1699902,0.00652531,0.01149176,0.002438357,0.02393328,0.4588541,0.05370065,0.00006582185,0.1622982,0.004649895],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01919173,0.01157385,0.9275696,0.03689275,0.003304356,0.0007395269,0.0001790882,0.0003197163,0.0002293916],"genre_scores_gemma":[0.9651961,0.003931967,0.02166723,0.005793923,0.0005518824,0.0001283541,0.00008186232,0.00009399316,0.002554686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9460044,"threshold_uncertainty_score":0.8592895,"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."}}