{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04610045,0.002174401,0.001908502,0.009090556,0.001353435,0.00727417,0.004477755,0.002772761,0.004300398],"category_scores_gemma":[0.07958902,0.0008884155,0.002485876,0.004706692,0.0009222794,0.002823394,0.002402247,0.001714504,0.003598525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004224434,"about_ca_system_score_gemma":0.007239289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120624,"about_ca_topic_score_gemma":0.009018221,"domain_scores_codex":[0.9819857,0.006706683,0.001735021,0.002034338,0.006957744,0.0005806285],"domain_scores_gemma":[0.954356,0.01772462,0.002885204,0.003051675,0.02125659,0.0007259865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008828393,0.0003010755,0.01482585,0.002974033,0.0005038921,0.000126017,0.0004671467,0.03388029,0.005611944,0.009370704,0.03481675,0.8962395],"study_design_scores_gemma":[0.0004673924,0.003675029,0.06880412,0.008648142,0.002223707,0.002328976,0.001302295,0.5433381,0.07522843,0.03945595,0.2538014,0.000726609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07657611,0.06000917,0.8025258,0.005162478,0.001599782,0.006485492,0.009065786,0.008293168,0.03028229],"genre_scores_gemma":[0.1821035,0.02021685,0.7599792,0.0008755146,0.000607645,0.005282335,0.0192533,0.003127893,0.008553802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04610045,"threshold_uncertainty_score":0.2438054,"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."}}