{"id":"W4411439184","doi":"10.1016/j.aej.2025.05.090","title":"M-CNN-RF: A hybrid deep learning model for accurate pediatric skeletal age estimation using hand bone radiographs","year":2025,"lang":"en","type":"article","venue":"Alexandria Engineering Journal","topic":"Forensic Anthropology and Bioarchaeology Studies","field":"Arts and Humanities","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Ministry of Science and ICT, South Korea; Institute for Information and Communications Technology Promotion; Shenzhen University; National Research Foundation of Korea; King Saud University; Korea Institute for Advancement of Technology; Ministry of Trade, Industry and Energy; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Radiography; Deep learning; Medicine; Artificial intelligence; Convolutional neural network; Bone age; Orthodontics; Computer science; Radiology; Internal 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002531826,0.0001985191,0.000299573,0.000392688,0.0011974,0.0001273957,0.0001011118,0.00006297826,0.00006190546],"category_scores_gemma":[0.0001283284,0.0001748549,0.000174541,0.00007207305,0.0009989719,0.0002108692,0.00004878359,0.0003113298,0.000002360142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003658923,"about_ca_system_score_gemma":0.00004136462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003502411,"about_ca_topic_score_gemma":0.000111305,"domain_scores_codex":[0.9990276,0.00002069748,0.000323767,0.0001702027,0.00008863911,0.0003690628],"domain_scores_gemma":[0.999504,0.0001311004,0.00012232,0.00007436365,0.0001151901,0.00005300925],"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":[0.0001524186,0.00007605377,0.001639939,0.0002720596,0.0006783092,0.0001374039,0.01027561,0.8754136,0.0002257249,0.104303,0.002543592,0.004282244],"study_design_scores_gemma":[0.0009187619,0.00009932968,0.0001365673,0.00005216867,0.0002751285,0.0001081693,0.0007091564,0.9934739,0.00005089302,0.002298299,0.001653321,0.0002242646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2536203,0.004439794,0.7388799,0.0005706352,0.001949649,0.000185594,0.000009882666,0.00009280389,0.0002514931],"genre_scores_gemma":[0.988619,0.00037361,0.009077337,0.00004923046,0.0006436612,0.00001104695,0.00001315085,0.0000199087,0.001193086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7349986,"threshold_uncertainty_score":0.9209551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02051809091793603,"score_gpt":0.2534340394484818,"score_spread":0.2329159485305458,"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."}}