{"id":"W4406134659","doi":"10.1016/j.inffus.2024.102892","title":"Oral multi-pathology segmentation with Lead-Assisting Backbone Attention Network and synthetic data generation","year":2025,"lang":"en","type":"article","venue":"Information Fusion","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Institute of Semiconductors, Chinese Academy of Sciences; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Lead (geology); Synthetic data; Artificial intelligence; Data science; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0004007788,0.0001175981,0.000120214,0.000192927,0.0003359918,0.000233249,0.00012047,0.00006767878,0.0000374083],"category_scores_gemma":[0.0000543948,0.0001069687,0.00002181089,0.0003535808,0.00005578303,0.002436445,0.0001421597,0.0001073965,0.00006070059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003451918,"about_ca_system_score_gemma":0.00001782195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004514317,"about_ca_topic_score_gemma":0.0001309673,"domain_scores_codex":[0.9990494,0.00007127946,0.0003537771,0.0001949748,0.0001684155,0.000162202],"domain_scores_gemma":[0.9993571,0.00002901049,0.0001909162,0.0003073343,0.00008645896,0.00002916328],"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":[0.0002357085,0.0001336735,0.1953184,0.0003092618,0.0001073701,0.0000266842,0.0007237031,0.001580773,0.03450952,0.001177344,0.01584002,0.7500376],"study_design_scores_gemma":[0.002617468,0.00006843233,0.4488459,0.0002899494,0.000146345,0.0002178542,0.001037314,0.5418314,0.001303084,0.0000582397,0.003277269,0.0003067258],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7013968,0.0001433294,0.295199,0.0001231815,0.0007605569,0.0003102751,0.00002432868,0.00009829413,0.001944163],"genre_scores_gemma":[0.980741,0.00004309981,0.01682963,0.0003191443,0.00006419916,0.00001581177,0.00177387,0.000006305474,0.0002069988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7497308,"threshold_uncertainty_score":0.4362055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02913065951302227,"score_gpt":0.2893341739943004,"score_spread":0.2602035144812781,"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."}}