{"id":"W2582769321","doi":"10.1002/mp.12124","title":"Classification and evaluation strategies of auto-segmentation approaches for PET: Report of AAPM task group No. 211","year":2017,"lang":"en","type":"article","venue":"Medical Physics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Segmentation; Algorithm; Artificial intelligence; Image segmentation; Task (project management); Machine learning; Data mining; Medical imaging","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":[0.0009058703,0.00008105458,0.0002282007,0.00002138516,0.00009074447,0.00001597109,0.0001128419,0.00006208181,0.00002730675],"category_scores_gemma":[0.0008136016,0.00006652124,0.00005484822,0.00003949914,0.0004138288,0.000122592,0.000034263,0.0001039893,0.000001111666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002236981,"about_ca_system_score_gemma":0.0001924503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003606574,"about_ca_topic_score_gemma":0.00000178538,"domain_scores_codex":[0.9986982,0.00002100429,0.0003651857,0.0002009947,0.0006218772,0.00009268376],"domain_scores_gemma":[0.9986837,0.00007711752,0.0004376777,0.0004362862,0.0002647499,0.000100492],"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":[0.0002218884,0.002372312,0.01476724,0.003145646,0.0002647204,0.00001543072,0.0007615712,0.000003769242,0.1866699,0.1170695,0.01777337,0.6569347],"study_design_scores_gemma":[0.007793066,0.001308307,0.2539122,0.001451159,0.001547953,0.0001630608,0.001237392,0.5186803,0.06232688,0.1431784,0.007855686,0.0005456019],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4428203,0.00008127096,0.5382722,0.008549311,0.0001550512,0.002290305,0.0000299567,0.00008418818,0.007717452],"genre_scores_gemma":[0.9843813,0.00004369904,0.01476305,0.00004368258,0.0001959913,0.0002268954,0.0002786393,0.00001068648,0.00005606584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6563891,"threshold_uncertainty_score":0.2712657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.137341375885745,"score_gpt":0.4016074920155457,"score_spread":0.2642661161298008,"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."}}