{"id":"W2923494043","doi":"10.1016/j.compbiomed.2019.03.015","title":"A multi-scale data fusion framework for bone age assessment with convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep learning; Feature extraction; Contourlet; Domain (mathematical analysis); Feature (linguistics); Data set; Machine learning; Scale (ratio); Artificial neural network; Data mining; Mathematics; Cartography; Geography","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":[0.0002683922,0.0001139825,0.0002596547,0.00008910904,0.00006267673,0.000008316729,0.0001929172,0.0001051754,0.0000273699],"category_scores_gemma":[0.00001536756,0.00008129339,0.00001985002,0.0001225806,0.0002984103,0.00007305393,0.0001585944,0.000247648,0.00000127125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001374604,"about_ca_system_score_gemma":0.000008702365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002638201,"about_ca_topic_score_gemma":0.00003775785,"domain_scores_codex":[0.9991412,0.0000515926,0.0001799704,0.0003590767,0.00005849434,0.0002096824],"domain_scores_gemma":[0.99927,0.000306659,0.00006620656,0.0002818606,0.00001708506,0.00005823233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000325136,0.0001362865,0.9725865,0.00006687811,0.00007301323,0.0001018459,0.0001262449,0.0001429095,0.0008143326,0.005064282,0.003410078,0.01715251],"study_design_scores_gemma":[0.003845626,0.0004037996,0.5704052,0.0002854672,0.00002907519,0.0001746369,0.0001301259,0.4218101,0.000001746582,0.0009449199,0.001830745,0.0001384907],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.379065,0.001652222,0.6163276,0.0004104706,0.002100774,0.0003230439,0.00002676046,0.00002542319,0.00006875397],"genre_scores_gemma":[0.9227666,0.00008832267,0.07520887,0.0009862306,0.0002699557,0.000009368579,0.0006291361,0.000007375046,0.00003418588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5437016,"threshold_uncertainty_score":0.3315049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02907664103159235,"score_gpt":0.3550725002872839,"score_spread":0.3259958592556915,"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."}}