{"id":"W4226199676","doi":"10.5167/uzh-214495","title":"Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge","year":2021,"lang":"en","type":"article","venue":"Zurich Open Repository and Archive (University of Zurich)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Commission","keywords":"Generalizability theory; Benchmarking; Segmentation; Computer science; Deep learning; Vendor; Artificial intelligence; Scanner; Field (mathematics); Cardiac imaging; Image segmentation; Data science; Machine learning; Medical physics; Data mining; Medicine; Radiology; Business","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003684833,0.0001538427,0.0003278411,0.00005830635,0.0005985756,0.00006046024,0.0002062863,0.00004170066,0.00003831503],"category_scores_gemma":[0.0001052096,0.0001367351,0.0001032495,0.0001155434,0.0003384385,0.000177103,0.0005027566,0.0003069798,0.000004288582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002292234,"about_ca_system_score_gemma":0.0001188366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003704791,"about_ca_topic_score_gemma":0.00003664244,"domain_scores_codex":[0.9985773,0.0004723009,0.0001477054,0.0004137168,0.0001896727,0.0001992818],"domain_scores_gemma":[0.9988708,0.0002778565,0.0001260089,0.0002944379,0.00009063982,0.0003402806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002118335,0.005829973,0.6341223,0.002144648,0.002900542,0.01020973,0.05677919,0.0001830518,0.1714954,0.00181559,0.0215051,0.0908962],"study_design_scores_gemma":[0.01455485,0.0002708619,0.8454717,0.0006007307,0.001204808,0.0002640592,0.01951288,0.07044919,0.001068895,0.00008819455,0.04589607,0.0006177192],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9344606,0.009112096,0.03882632,0.01052316,0.0005670245,0.001647507,0.0001017779,0.00008527963,0.004676207],"genre_scores_gemma":[0.807934,0.003738171,0.1691081,0.0005519154,0.0002080105,0.000003401879,0.0001352711,0.00004344922,0.01827765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2113495,"threshold_uncertainty_score":0.5575894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01784446899483396,"score_gpt":0.2571554625033866,"score_spread":0.2393109935085526,"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."}}