{"id":"W1568813557","doi":"10.1111/cid.12217","title":"Segmentation of Trabecular Jaw Bone on Cone Beam <scp>CT</scp> Datasets","year":2014,"lang":"en","type":"article","venue":"Clinical Implant Dentistry and Related Research","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Thresholding; Cone beam computed tomography; Segmentation; Ground truth; Jaw bone; Context (archaeology); Image segmentation; Computer science; Artificial intelligence; Computer vision; Medicine; Biomedical engineering; Computed tomography; Implant; Radiology; Image (mathematics); Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003718918,0.0002106913,0.0004904087,0.0002996581,0.0003398418,0.000148024,0.0003593898,0.0002627217,0.00008892729],"category_scores_gemma":[0.001410088,0.0001858026,0.0002408718,0.000565012,0.0009243354,0.0002256435,0.000203194,0.001437816,0.000523862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001657173,"about_ca_system_score_gemma":0.00003369739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004626454,"about_ca_topic_score_gemma":0.00000677914,"domain_scores_codex":[0.9959337,0.0009033071,0.001057349,0.0006618343,0.0008562586,0.000587526],"domain_scores_gemma":[0.9958541,0.002841842,0.000245349,0.0005704018,0.0001138156,0.0003744548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001055033,0.005987753,0.06147178,0.001745297,0.00302564,0.08525357,0.0003933627,0.00004742606,0.2566865,0.008299035,0.4409288,0.1351058],"study_design_scores_gemma":[0.02289373,0.003772902,0.3777732,0.001839668,0.0008609609,0.1470761,0.002925912,0.002823261,0.3082262,0.007950227,0.1228912,0.0009667077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931586,0.0006886077,0.00008637247,0.00007115061,0.002915339,0.000324438,0.0006797467,0.0000500983,0.002025585],"genre_scores_gemma":[0.9959825,0.0005385145,0.00009609938,0.00007344723,0.00009365552,0.00001172044,0.001326424,0.0000270905,0.001850573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3180377,"threshold_uncertainty_score":0.757681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06908810318757679,"score_gpt":0.4197878674208546,"score_spread":0.3506997642332778,"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."}}