{"id":"W4312211566","doi":"10.3390/s22249877","title":"Dual-Stage Deeply Supervised Attention-Based Convolutional Neural Networks for Mandibular Canal Segmentation in CBCT Scans","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Convolutional neural network; Mandibular canal; Visibility; Computer vision; Deep learning; Residual; Orthodontics; Medicine; Algorithm","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004720175,0.0008243215,0.0005653524,0.0006099197,0.0002406369,0.0004056092,0.001296936,0.000890783,0.001355073],"category_scores_gemma":[0.00112928,0.0003644464,0.0006498112,0.0004509081,0.0003259935,0.0006169439,0.000737704,0.0007232081,0.0004246166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000640302,"about_ca_system_score_gemma":0.0008583848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009951206,"about_ca_topic_score_gemma":0.01981315,"domain_scores_codex":[0.9997419,0.0000282564,0.00001506393,0.00008239815,0.00007165767,0.0000608515],"domain_scores_gemma":[0.9996564,0.0001126363,0.00004358304,0.00005066074,0.0001135169,0.00002306978],"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":[0.0004679291,0.0002049846,0.003468068,0.0001713549,0.0001131369,0.0002512744,0.0001150608,0.1897274,0.07670223,0.001225523,0.003568073,0.7239851],"study_design_scores_gemma":[0.000008063023,0.00006583118,0.001205771,0.00001052975,0.00003075764,0.00008391613,0.00001315976,0.983559,0.01371093,0.0006434306,0.0006591678,0.000009486232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1843062,0.001748418,0.805057,0.0003208302,0.0001027255,0.0001263492,0.0004073184,0.005078747,0.002852459],"genre_scores_gemma":[0.7869005,0.0005787365,0.205105,0.0003300325,0.00006640042,0.0001067598,0.001065413,0.0001656422,0.005681425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009951206,"threshold_uncertainty_score":0.01978654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01421576557384788,"score_gpt":0.2567410511132834,"score_spread":0.2425252855394355,"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."}}