{"id":"W4308529557","doi":"10.1016/j.jdent.2022.104345","title":"Temporomandibular joint segmentation in MRI images using deep learning","year":2022,"lang":"en","type":"article","venue":"Journal of Dentistry","topic":"Temporomandibular Joint Disorders","field":"Health Professions","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"Telus (Canada); University of Alberta","funders":"","keywords":"Temporomandibular joint; Condyle; Segmentation; Magnetic resonance imaging; Artificial intelligence; Computer science; Convolutional neural network; Population; Medicine; Anatomy; Orthodontics; Radiology","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":[0.001845346,0.0001267965,0.0003294871,0.0003595644,0.0008317721,0.0000184928,0.0001818499,0.00007336532,0.001264464],"category_scores_gemma":[0.0001620233,0.000131697,0.0001210864,0.0002861617,0.00002971123,0.0002899716,0.0001949379,0.001673476,0.00001747425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006607671,"about_ca_system_score_gemma":0.0002342225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091229,"about_ca_topic_score_gemma":0.00004464428,"domain_scores_codex":[0.996789,0.001076648,0.001073536,0.0001504154,0.0005809444,0.0003294117],"domain_scores_gemma":[0.9983428,0.0001093588,0.001233599,0.0001293964,0.00009466389,0.00009016084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001787403,0.0002851121,0.9049803,0.0002846374,0.0001192369,0.002327082,0.006010078,0.01333885,0.06513337,0.00006589244,0.006545622,0.0007310799],"study_design_scores_gemma":[0.01549123,0.001072454,0.7619085,0.001106962,0.0003068742,0.003966653,0.1678119,0.004753313,0.002495869,0.003144908,0.03686713,0.001074222],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892336,0.001242438,0.006798941,0.0006799588,0.001375419,0.0002557112,0.000004774821,0.00002042955,0.0003887537],"genre_scores_gemma":[0.9925783,0.00005794226,0.006470961,0.0001359741,0.0001509962,0.00001402898,0.000013612,0.00003342528,0.0005447125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1618018,"threshold_uncertainty_score":0.9996485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04395717711066265,"score_gpt":0.3874302798147715,"score_spread":0.3434731027041088,"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."}}