{"id":"W1968694013","doi":"10.1016/j.compmedimag.2006.07.003","title":"Multistage graph-based segmentation of thoracoscopic images","year":2006,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Thresholding; Computer science; Segmentation; Computer vision; Pattern recognition (psychology); Smoothing; Image segmentation; Cut; Histogram; Image (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":[0.0002771979,0.0001616877,0.0002874596,0.0002294722,0.00006169828,0.00004009689,0.0001321472,0.00006026365,0.00003360449],"category_scores_gemma":[0.00004188228,0.0001455425,0.00009170067,0.0003414517,0.000337426,0.00007350528,0.00002695327,0.0002176172,0.000001404703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007603442,"about_ca_system_score_gemma":0.00002139978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009181092,"about_ca_topic_score_gemma":0.00000267509,"domain_scores_codex":[0.9987693,0.00005246831,0.0003558499,0.0001919358,0.0004075216,0.0002228559],"domain_scores_gemma":[0.9994152,0.0001493732,0.00005094741,0.0001581689,0.00004933368,0.0001770172],"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":[0.00003074318,0.0006855892,0.1451672,0.003325582,0.0003948545,0.0004674816,0.0003050653,0.005147501,0.1172191,0.002672701,0.03209842,0.6924857],"study_design_scores_gemma":[0.001583188,0.00001208515,0.008558108,0.0003214651,0.00008324176,0.0000116753,0.00002775515,0.9790472,0.007613255,0.001168655,0.001304525,0.0002687853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.166585,0.002123569,0.8296322,0.000691935,0.0003097113,0.00007803324,0.00001389285,0.0003281444,0.0002375636],"genre_scores_gemma":[0.9835858,0.0002747302,0.01559199,0.0003144362,0.0001180982,0.000007341281,0.00006889907,0.00002253098,0.00001613685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9738998,"threshold_uncertainty_score":0.593505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005010055227317554,"score_gpt":0.2377177768983647,"score_spread":0.2327077216710471,"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."}}