{"id":"W4411664870","doi":"10.3389/fdmed.2025.1583455","title":"Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans","year":2025,"lang":"en","type":"article","venue":"Frontiers in Dental Medicine","topic":"Orthodontics and Dentofacial Orthopedics","field":"Dentistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Receiver operating characteristic; Convolutional neural network; Artificial intelligence; Computer science; Robustness (evolution); Pattern recognition (psychology); Cone beam computed tomography; Contextual image classification; Surgical planning; Medicine; Computed tomography; Radiology; Machine learning; Image (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002723926,0.000189878,0.0003786289,0.0004048471,0.0000890653,0.00002023828,0.0001722395,0.0002257535,0.00004402388],"category_scores_gemma":[0.000153011,0.0001748675,0.00008099486,0.0006703507,0.0002399143,0.0001237661,0.00004696101,0.000309185,0.000002667032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002350002,"about_ca_system_score_gemma":0.00006431699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000160269,"about_ca_topic_score_gemma":0.000147257,"domain_scores_codex":[0.9983011,0.0001025419,0.0006011073,0.0003027185,0.0004515046,0.0002410407],"domain_scores_gemma":[0.999303,0.00005128781,0.0002330296,0.0002441502,0.00009750608,0.00007103638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003835413,0.00008709897,0.9715357,0.0000583114,0.00005909638,0.0000554359,0.00006977924,0.005039212,0.0008686436,0.001529162,0.01861065,0.001703402],"study_design_scores_gemma":[0.0009370466,0.00004894836,0.5141117,0.0001859284,0.0000517375,0.00001391972,0.0003297206,0.4839514,0.00004675294,0.00003829038,0.0002020159,0.00008259693],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9394725,0.0008294539,0.04769675,0.0002062318,0.01014135,0.0003391302,0.00004072591,0.0001029252,0.001170948],"genre_scores_gemma":[0.9976656,0.00002579535,0.001142025,0.0001813274,0.0003275805,0.000006548995,0.0002893062,0.00001568271,0.0003461409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4789121,"threshold_uncertainty_score":0.713089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02044539650199919,"score_gpt":0.3072718975061359,"score_spread":0.2868265010041367,"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."}}