{"id":"W2980254319","doi":"10.1109/embc.2019.8857060","title":"Fully Automated Segmentation of Alveolar Bone Using Deep Convolutional Neural Networks from Intraoral Ultrasound Images","year":2019,"lang":"en","type":"article","venue":"","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Segmentation; Hausdorff distance; Ultrasound; Dental alveolus; Ground truth; Deep learning; Radiography; Computer vision; Pattern recognition (psychology); Radiology; Medicine; Orthodontics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001096854,0.0001597563,0.0002276599,0.0001159604,0.00007237065,0.00009358469,0.0001286784,0.00007811319,0.001774829],"category_scores_gemma":[0.00001552844,0.0001607656,0.0001547383,0.0002812718,0.0001084747,0.0006169553,0.00003996995,0.0001467935,0.00006373813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004789329,"about_ca_system_score_gemma":0.00001468889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007945054,"about_ca_topic_score_gemma":0.00003743023,"domain_scores_codex":[0.9987446,0.00007594276,0.0003741074,0.0002635197,0.0002859975,0.0002558404],"domain_scores_gemma":[0.999369,0.0001266667,0.0001736496,0.0001867606,0.00007927311,0.0000646369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008607536,0.00009145148,0.6096798,0.00002076122,0.0001563837,0.00002654963,0.00007634727,0.01132301,0.3767811,0.0001312977,0.0009618897,0.0006653478],"study_design_scores_gemma":[0.0009670852,0.00003051306,0.4483044,0.00002352393,0.00007011407,0.0001234655,0.0004278063,0.5363497,0.01339165,0.0001077811,0.0000083833,0.0001955603],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9749949,0.0005952382,0.02235719,0.000009700752,0.00100487,0.0001832197,0.00006806614,0.0002218397,0.0005649708],"genre_scores_gemma":[0.9929654,0.00000708019,0.006355196,0.000113496,0.000104205,0.000002241592,0.00032452,0.0000196426,0.0001082196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5250267,"threshold_uncertainty_score":0.9991377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00829606782996054,"score_gpt":0.2554174710629855,"score_spread":0.2471214032330249,"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."}}