{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008630728,0.0001855372,0.0005017503,0.00007413166,0.0003871578,0.0001908164,0.0002218767,0.00006295886,0.0007762732],"category_scores_gemma":[0.007929001,0.0001669801,0.00007166871,0.0001589019,0.0004183752,0.0005093584,0.0001092018,0.0002732532,0.00001344086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007714628,"about_ca_system_score_gemma":0.00002444006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001006791,"about_ca_topic_score_gemma":0.0001012288,"domain_scores_codex":[0.998321,0.00009343915,0.0003989882,0.000305294,0.0005713094,0.0003099975],"domain_scores_gemma":[0.9977123,0.001403288,0.00009874004,0.0004151582,0.0001283112,0.0002422433],"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":[0.0006486004,0.0004681502,0.1082649,0.00253087,0.02418937,0.002137094,0.01738494,0.002379933,0.2358944,0.004191143,0.009528115,0.5923826],"study_design_scores_gemma":[0.01771497,0.0009583502,0.4366959,0.001237163,0.01796263,0.00006953243,0.06157104,0.2537286,0.115865,0.07710745,0.00850751,0.00858177],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04594913,0.0004210091,0.9521943,0.0002703593,0.00006363987,0.00007035604,0.0001186178,0.0001272389,0.0007853152],"genre_scores_gemma":[0.7904884,0.0006649154,0.2086058,0.0001068795,0.0000412816,0.00001522303,0.00002763236,0.00001842949,0.00003149529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7445393,"threshold_uncertainty_score":0.9492328,"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."}}