{"id":"W4413355910","doi":"10.1016/j.compbiomed.2025.110960","title":"Automatic margin line extraction using 3D deep learning on digital surface models of prepared teeth for crown generation","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"InterDigital (Canada); Polytechnique Montréal","funders":"MEDTEQ+; Natural Sciences and Engineering Research Council of Canada; King Fahd University of Petroleum and Minerals","keywords":"Crown (dentistry); Margin (machine learning); Computer science; Line (geometry); Extraction (chemistry); Artificial intelligence; Surface (topology); Deep learning; Geology; Pattern recognition (psychology); Orthodontics; Machine learning; Mathematics; Chemistry; Geometry; Medicine; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002034204,0.00008795741,0.0002105939,0.0001772792,0.00006702639,0.000009820216,0.00005181395,0.00007649595,0.000005376308],"category_scores_gemma":[0.00007078279,0.00007581777,0.00002911784,0.0001509427,0.0001491116,0.0001161507,0.00002357148,0.0001059531,2.325764e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002502486,"about_ca_system_score_gemma":0.000009917154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002265761,"about_ca_topic_score_gemma":0.000008000024,"domain_scores_codex":[0.9993557,0.00005118926,0.0002509271,0.0001893719,0.00003997142,0.0001128291],"domain_scores_gemma":[0.9995687,0.0002091485,0.00009284782,0.00007899338,0.00002970888,0.00002059059],"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":[0.0008705845,0.000439586,0.1145251,0.0008238786,0.0003909325,0.00003610956,0.002243526,0.1558918,0.1443363,0.009649846,0.001076094,0.5697163],"study_design_scores_gemma":[0.001116184,0.0001907211,0.006510895,0.0002922324,0.00002662492,0.00001939846,0.00010699,0.9891563,0.0007678498,0.00163754,0.0001114478,0.00006382634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6707212,0.0005548527,0.3276464,0.0000498131,0.0006311685,0.0001370768,0.000002511811,0.00001723689,0.0002397125],"genre_scores_gemma":[0.9932173,0.00004599929,0.006434832,0.00008911199,0.0000805887,0.000003245752,0.0000684266,0.000004529687,0.00005593727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8332645,"threshold_uncertainty_score":0.3091759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03005530910969555,"score_gpt":0.3473871386434293,"score_spread":0.3173318295337338,"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."}}