{"id":"W4404481676","doi":"10.1007/s10278-024-01282-9","title":"RIDGE: Reproducibility, Integrity, Dependability, Generalizability, and Efficiency Assessment of Medical Image Segmentation Models","year":2024,"lang":"en","type":"article","venue":"Journal of Imaging Informatics in Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Calgary","funders":"Lunit; Radiological Society of North America; Gordon and Betty Moore Foundation; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Generalizability theory; Dependability; Checklist; Segmentation; Computer science; Artificial intelligence; Reproducibility; Deep learning; Data mining; Machine learning; Software engineering; Psychology; Mathematics","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":[0.0162461,0.0001569403,0.0005797619,0.0006257975,0.00004236579,0.00004075014,0.0002063117,0.0001035485,0.0001345007],"category_scores_gemma":[0.003476944,0.0001099794,0.00008376835,0.0005179236,0.0005224401,0.0007114643,0.000109636,0.001034993,0.000001278215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003502738,"about_ca_system_score_gemma":0.001164394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004706356,"about_ca_topic_score_gemma":0.0000267035,"domain_scores_codex":[0.9952058,0.0001392813,0.002719732,0.0002222341,0.001492348,0.0002205791],"domain_scores_gemma":[0.997554,0.0005562707,0.000443205,0.000460948,0.0007499178,0.0002356492],"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":[0.0002501076,0.001304037,0.4380721,0.01576133,0.0001643355,0.0002237062,0.06986848,0.00108084,0.004750153,0.007011606,0.006431655,0.4550817],"study_design_scores_gemma":[0.0006110109,0.001050391,0.0115551,0.005719825,0.0002168122,0.001897757,0.01936476,0.9215547,0.00423921,0.03338432,0.0002096577,0.0001964959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8753067,0.001822009,0.09042273,0.02986716,0.001174834,0.000402687,0.000003401633,0.00002154794,0.0009789831],"genre_scores_gemma":[0.9768425,0.001315316,0.02090109,0.0005540933,0.0003515199,0.000004558767,0.0000105947,0.00001202504,0.000008294122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9204738,"threshold_uncertainty_score":0.5630606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1363594050263097,"score_gpt":0.5029321918665249,"score_spread":0.3665727868402152,"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."}}