{"id":"W2146865307","doi":"10.1109/tpami.2004.1273940","title":"A statistical model for contours in images","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal","funders":"","keywords":"Artificial intelligence; Statistical model; Computer science; Image segmentation; Segmentation; Pattern recognition (psychology); Expectation–maximization algorithm; Markov random field; Iterated function; Simulated annealing; Algorithm; Mathematics; 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":[0.0002296003,0.0001315592,0.0002254643,0.0003900717,0.00006984895,0.00008492645,0.0002727556,0.00004154568,0.00003717658],"category_scores_gemma":[0.00001111138,0.0001168463,0.0001014961,0.0004614402,0.00007207699,0.000206794,0.00000301601,0.0001531144,0.000004900091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004723961,"about_ca_system_score_gemma":0.00003071066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007837056,"about_ca_topic_score_gemma":0.001243534,"domain_scores_codex":[0.9988925,0.00003314744,0.0003153383,0.000377609,0.0001944386,0.0001869597],"domain_scores_gemma":[0.9993944,0.0001476175,0.00005170044,0.0002453662,0.00004961466,0.0001113115],"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":[0.00001021169,0.0002114756,0.00007796481,0.00001543229,0.0000951597,0.0000094181,0.0004320534,0.07910649,0.0005225613,0.0005585228,0.00001197823,0.9189487],"study_design_scores_gemma":[0.0001922141,0.00009622348,0.0001914469,0.00001671525,0.00009477989,0.00000278015,0.00002262603,0.7776835,0.2163425,0.005207237,0.000001334545,0.0001486534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002378497,0.00002459194,0.9987708,0.0005756349,0.00003792169,0.0001885209,0.00007442606,0.00007481636,0.00001541884],"genre_scores_gemma":[0.8408649,0.00009831518,0.1582477,0.0006498634,0.00000392895,0.00007034188,0.000004372977,0.000005471167,0.00005513467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9188001,"threshold_uncertainty_score":0.4764855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02626716470366291,"score_gpt":0.3198691011978763,"score_spread":0.2936019364942134,"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."}}