{"id":"W2138181193","doi":"10.1109/isbi.2004.1398479","title":"Anatomical guided segmentation with non-stationary tissue class distributions in an expectation-maximization framework","year":2005,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Research Resources; National Cancer Institute; National Institute of Mental Health","keywords":"Class (philosophy); Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Expectation–maximization algorithm; Maximization; Image segmentation; Mathematics; Mathematical optimization; Maximum likelihood; Statistics","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":[0.0001729827,0.0001511676,0.0001394208,0.000228408,0.0001128007,0.0001651943,0.0004055724,0.00009969294,0.0002826101],"category_scores_gemma":[0.00009126163,0.0001380706,0.0000184482,0.0008532309,0.00007093669,0.00225841,0.00005577744,0.0001658575,0.00004702312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002486873,"about_ca_system_score_gemma":0.0001157385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000031514,"about_ca_topic_score_gemma":0.00009718922,"domain_scores_codex":[0.9983385,0.0001127931,0.000430279,0.0004288611,0.0004567991,0.0002327767],"domain_scores_gemma":[0.9990039,0.0001422979,0.0001233162,0.0003779378,0.000197522,0.0001549956],"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":[0.00009002507,0.002245122,0.0216026,0.00005893533,0.00005447946,0.00008866578,0.01365189,0.01276415,0.04536512,0.1678754,0.01622792,0.7199757],"study_design_scores_gemma":[0.001797308,0.0004759055,0.02836308,0.0001091058,0.00001635903,0.00003509134,0.001250051,0.5671498,0.3909663,0.008724939,0.0003381843,0.0007739246],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02981541,0.000006541955,0.9665189,0.002258058,0.00004987425,0.0004471643,0.000005668271,0.000353098,0.0005452463],"genre_scores_gemma":[0.3842952,0.00000584841,0.6147329,0.0005675217,0.00004144305,0.0001038993,0.0001873701,0.000008213812,0.00005761575],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7192018,"threshold_uncertainty_score":0.5630354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01364710552249629,"score_gpt":0.3218911512577876,"score_spread":0.3082440457352913,"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."}}