{"id":"W4362560246","doi":"10.1016/j.media.2023.102808","title":"MyoPS: A benchmark of myocardial pathology segmentation combining three-sequence cardiac magnetic resonance images","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Benchmark (surveying); Computer science; Preprocessor; Artificial intelligence; Cardiac magnetic resonance; Myocardial infarction; Magnetic resonance imaging; Image segmentation; Medical physics; Medicine; Pattern recognition (psychology); Radiology; Cardiology","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":[0.0005603704,0.0001421759,0.0006011028,0.0003209968,0.00007776146,0.000009640756,0.0001578259,0.0001215248,0.0004872872],"category_scores_gemma":[0.0003587662,0.0001265184,0.0003473566,0.002336571,0.0003862352,0.00007774781,0.00009953268,0.0002275335,0.00004389741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003993164,"about_ca_system_score_gemma":0.00008234147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009387889,"about_ca_topic_score_gemma":0.00001109814,"domain_scores_codex":[0.9982156,0.00007051188,0.0004480756,0.000374068,0.0006111701,0.0002805642],"domain_scores_gemma":[0.9988751,0.0001861034,0.0001216127,0.0004665864,0.0001684596,0.0001821452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001423437,0.000416987,0.1581513,0.0001797947,0.0007080088,0.001147398,0.0006624634,0.0001179239,0.2405967,0.001270618,0.01544157,0.581165],"study_design_scores_gemma":[0.004096988,0.001504184,0.8251038,0.0005089769,0.01235875,0.0001090232,0.001807446,0.06247957,0.06748956,0.009829028,0.01345431,0.001258403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3902226,0.004357787,0.5891879,0.007918507,0.000173929,0.001280308,0.0003190248,0.000824794,0.00571517],"genre_scores_gemma":[0.910261,0.003639562,0.08323734,0.0006795963,0.0002055165,0.0004019201,0.0008636574,0.00004093209,0.0006704764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6669525,"threshold_uncertainty_score":0.5335453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768570160716264,"score_gpt":0.3377404210989619,"score_spread":0.3200547194917993,"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."}}