{"id":"W4391722237","doi":"10.1016/j.heliyon.2024.e25892","title":"Semantic segmentation for tooth cracks using improved DeepLabv3+ model","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Guangzhou Science and Technology Program key projects; National Natural Science Foundation of China; Sun Yat-sen University; Guangzhou University; Guangdong University of Technology; China Scholarship Council","keywords":"Segmentation; Computer science; Artificial intelligence; Computer vision; Orthodontics; Psychology; Dentistry; Medicine","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":[0.000508804,0.001251707,0.0007472977,0.0008943033,0.000396548,0.0008179924,0.002046661,0.001542388,0.002795409],"category_scores_gemma":[0.0009396278,0.0004178267,0.0009534259,0.0004736464,0.0003849225,0.001060127,0.0007889994,0.0009531403,0.0008623468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350724,"about_ca_system_score_gemma":0.00146703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02113457,"about_ca_topic_score_gemma":0.02430341,"domain_scores_codex":[0.9997916,0.00002046572,0.00001008343,0.00008196045,0.00005283565,0.00004311217],"domain_scores_gemma":[0.9997577,0.000054161,0.00002552414,0.00003109973,0.0001059178,0.00002563621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007371877,0.0003849913,0.004516092,0.0002700253,0.0002221416,0.0001907361,0.0001096265,0.4872252,0.03816804,0.002770743,0.01398266,0.4514225],"study_design_scores_gemma":[0.00001075679,0.00004983474,0.0002904944,0.000007479166,0.00001619126,0.00002140344,0.000009413534,0.9937845,0.004309489,0.0008814296,0.0006130804,0.000005824774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2351006,0.001675883,0.7347734,0.0008251463,0.0002875064,0.0002373896,0.002063353,0.01849649,0.006540299],"genre_scores_gemma":[0.809244,0.0004032386,0.1775016,0.0006660091,0.00005880293,0.000251694,0.003927953,0.0004191179,0.007527493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02113457,"threshold_uncertainty_score":0.04202312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0253783480612344,"score_gpt":0.3121182643337095,"score_spread":0.2867399162724751,"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."}}