{"id":"W2738318712","doi":"10.1016/j.media.2017.07.004","title":"Designing image segmentation studies: Statistical power, sample size and reference standard quality","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Medical Research Council; Radboud Universiteit; Cancer Research UK","keywords":"Resampling; Sample size determination; Segmentation; Computer science; Reference data; Statistics; Range (aeronautics); Standard deviation; Matching (statistics); Sample (material); Statistical power; Data set; Artificial intelligence; Mathematics; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3920904,0.001569141,0.00363642,0.00302614,0.001675761,0.005418736,0.003659991,0.006338288,0.002930909],"category_scores_gemma":[0.7120556,0.001645895,0.003315089,0.003229874,0.007566846,0.006159466,0.004048952,0.003923688,0.001137786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002073177,"about_ca_system_score_gemma":0.004868013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001653743,"about_ca_topic_score_gemma":0.001417602,"domain_scores_codex":[0.6327947,0.3071418,0.0162311,0.01249672,0.02996964,0.001365975],"domain_scores_gemma":[0.2811445,0.6353645,0.02669155,0.03295309,0.02276774,0.001078687],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009410967,0.001240707,0.08359899,0.009624899,0.007802896,0.001025672,0.006717747,0.07591683,0.01577365,0.1212237,0.01492641,0.6527376],"study_design_scores_gemma":[0.008113659,0.01750286,0.1124235,0.008218555,0.006014443,0.002353729,0.002108531,0.2100491,0.05560054,0.5047778,0.0717734,0.001063796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02894893,0.003434127,0.952836,0.003528843,0.0004682288,0.006488367,0.0004794988,0.0005174477,0.003298635],"genre_scores_gemma":[0.3655354,0.00132551,0.6056139,0.002157919,0.0003509969,0.02337599,0.0004255068,0.0004884904,0.0007263745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6079096,"threshold_uncertainty_score":0.7496607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03164478710718117,"score_gpt":0.3839955934075969,"score_spread":0.3523508063004158,"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."}}