{"id":"W4391109864","doi":"10.1038/s41467-024-44824-z","title":"Segment anything in medical images","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":2390,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Vector Institute; University of Toronto; University Health Network","funders":"Alliance de recherche numérique du Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Computational biology; Medicine; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001917254,0.001432522,0.001006415,0.002875607,0.0006014213,0.002486037,0.001594431,0.002561263,0.005629494],"category_scores_gemma":[0.007271822,0.0007168873,0.002138111,0.001934796,0.00115753,0.002097971,0.002173521,0.001614444,0.003857714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125702,"about_ca_system_score_gemma":0.001511092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004637292,"about_ca_topic_score_gemma":0.007959773,"domain_scores_codex":[0.9984388,0.0002816716,0.0001214896,0.0006594551,0.0003727619,0.0001258133],"domain_scores_gemma":[0.9982775,0.0007890042,0.000159929,0.0004266051,0.000255785,0.00009114575],"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":[0.001049837,0.0002205948,0.009588771,0.00153554,0.0003776177,0.0007672717,0.0004930318,0.08523431,0.0469442,0.01806978,0.05760357,0.7781155],"study_design_scores_gemma":[0.00008282121,0.0003810295,0.009450681,0.0004660317,0.0002199078,0.002400353,0.0003539373,0.7714363,0.05390241,0.06063429,0.1005684,0.000103868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05329968,0.006966325,0.9031878,0.003593712,0.0004882274,0.0009125439,0.01055335,0.01256343,0.008435029],"genre_scores_gemma":[0.3002639,0.005065479,0.6552515,0.00222886,0.0004640113,0.0005543237,0.02572734,0.001576408,0.008868156],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005629494,"threshold_uncertainty_score":0.0188325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01669069355708667,"score_gpt":0.3341284663747068,"score_spread":0.3174377728176201,"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."}}