{"id":"W3022602416","doi":"10.1177/0022034520920593","title":"Alveolar Bone Segmentation in Intraoral Ultrasonographs with Machine Learning","year":2020,"lang":"en","type":"article","venue":"Journal of Dental Research","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Alberta Innovates - Technology Futures; Women and Children's Health Research Institute","keywords":"Dental alveolus; Convolutional neural network; Ultrasound; Segmentation; Computer science; Alveolar crest; Medicine; Intraclass correlation; Alveolar process; Robustness (evolution); Artificial intelligence; Sørensen–Dice coefficient; Dentistry; Image segmentation; Radiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00117573,0.0004909426,0.0003163371,0.001999839,0.0002408088,0.0006843093,0.0005622234,0.0009253139,0.000977837],"category_scores_gemma":[0.002212064,0.0003675258,0.0004661297,0.0008406214,0.0004207144,0.0004953815,0.0005368313,0.0004598651,0.0004486738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004632028,"about_ca_system_score_gemma":0.0005834069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003263437,"about_ca_topic_score_gemma":0.006220594,"domain_scores_codex":[0.9994786,0.0001169001,0.00003851069,0.0001311092,0.0001745412,0.00006035515],"domain_scores_gemma":[0.9993483,0.000277399,0.000085214,0.00008884758,0.0001806799,0.00001950632],"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":[0.000451455,0.0001392974,0.007073774,0.0001955965,0.0000778602,0.0003512693,0.0002504502,0.075014,0.1686236,0.00129582,0.0008850317,0.7456419],"study_design_scores_gemma":[0.00001000945,0.0001051123,0.006843457,0.00002840501,0.00002986675,0.0003757184,0.00007900799,0.9354575,0.05446941,0.001096438,0.001483528,0.00002145536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1887631,0.0009239262,0.8066114,0.0001788769,0.00003914801,0.0001225149,0.0001106235,0.001675028,0.001575362],"genre_scores_gemma":[0.5551546,0.0003937547,0.4425053,0.00009339592,0.00002179968,0.00007522351,0.0001892992,0.00008757518,0.001479023],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003263437,"threshold_uncertainty_score":0.006488919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0428413613042753,"score_gpt":0.3508585082891062,"score_spread":0.3080171469848309,"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."}}