{"id":"W2042797201","doi":"10.1371/journal.pone.0020241","title":"Automated Analysis of Craniofacial Morphology Using Magnetic Resonance Images","year":2011,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Orthodontics and Dentofacial Orthopedics","field":"Dentistry","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cégep de Jonquière; Université du Québec à Chicoutimi; Centre Hospitalier de l’Université de Montréal; McGill University; Baycrest Hospital; Montreal Neurological Institute and Hospital; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Government of Ontario; Heart And Stroke Foundation Of Quebec; University of Toronto; Compute Canada; Heart and Stroke Foundation of Canada","keywords":"Craniofacial; Artificial intelligence; Population; Image warping; Pattern recognition (psychology); Computer science; Magnetic resonance imaging; Principal component analysis; Landmark; Voxel; Forehead; Sagittal plane; Computer vision; Anatomy; Biology; Medicine; Radiology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001088669,0.0006103165,0.0006263052,0.004131536,0.0004031059,0.001327443,0.0007496414,0.0004412271,0.002218636],"category_scores_gemma":[0.003374152,0.0004192638,0.0005910672,0.001482871,0.0003798277,0.0007188075,0.000696288,0.0004619188,0.001267467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003509257,"about_ca_system_score_gemma":0.0007378901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004561469,"about_ca_topic_score_gemma":0.007893094,"domain_scores_codex":[0.9992635,0.0001629262,0.00005538047,0.0002103168,0.0002644626,0.00004340446],"domain_scores_gemma":[0.9988592,0.0003544966,0.0002221516,0.0002165381,0.0003204932,0.00002706157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001500956,0.00007917642,0.02070392,0.0002443981,0.0001462617,0.0002806416,0.0003881203,0.01702114,0.1897505,0.001888248,0.002910177,0.7664374],"study_design_scores_gemma":[0.00006487586,0.0003103404,0.3447576,0.0001345721,0.0002149997,0.001930309,0.001156308,0.5087535,0.1116876,0.00970654,0.02106832,0.0002151088],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1550327,0.0006710736,0.8351313,0.0002074209,0.00003763728,0.0003707779,0.001348659,0.004250112,0.002950308],"genre_scores_gemma":[0.2800466,0.0008728786,0.7148621,0.00007102099,0.00005229129,0.0002749723,0.001736717,0.0005264669,0.001556932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004561469,"threshold_uncertainty_score":0.00906986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08532706571480934,"score_gpt":0.2819725096177708,"score_spread":0.1966454439029614,"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."}}