{"id":"W2994569435","doi":"10.2196/16291","title":"Age Assessment of Youth and Young Adults Using Magnetic Resonance Imaging of the Knee: A Deep Learning Approach","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Forensic Anthropology and Bioarchaeology Studies","field":"Arts and Humanities","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Socialstyrelsen","keywords":"Bone age; Deep learning; Magnetic resonance imaging; Convolutional neural network; Artificial intelligence; Transfer of learning; Computer science; Young adult; Machine learning; Medicine; Radiology; Gerontology; Anatomy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002283235,0.00009365682,0.0002308795,0.00003938888,0.0001587376,0.000007599898,0.0001234108,0.00005801912,0.0001613259],"category_scores_gemma":[0.0000336978,0.00005615551,0.0000442826,0.0000356672,0.007474076,0.00008775936,0.0002352457,0.0002845326,0.000001083992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009569038,"about_ca_system_score_gemma":0.0000356771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000359319,"about_ca_topic_score_gemma":0.0002244327,"domain_scores_codex":[0.9990858,0.00004375204,0.0003706779,0.00006128744,0.0002755235,0.0001629669],"domain_scores_gemma":[0.9995506,0.00004849856,0.000189164,0.0001165547,0.00006413054,0.0000310114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004154202,0.00008643477,0.2777842,0.0007334235,0.00004218129,0.000002663539,0.6099612,0.000008701199,0.000001490436,0.09505095,0.00007870241,0.01620848],"study_design_scores_gemma":[0.001393117,0.0003081832,0.02651354,0.0005346084,0.00006782755,0.00003184716,0.8070933,0.1614756,0.000009000386,0.0001957702,0.002177116,0.0002001615],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804544,0.0009060346,0.00007809707,0.0001387302,0.000278659,0.0002264777,0.000006972542,0.00001360432,0.01789706],"genre_scores_gemma":[0.9987805,0.00006430578,0.0006909621,0.0001227769,0.00003847815,0.000004002348,0.000004838424,0.000004544299,0.0002896082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2512707,"threshold_uncertainty_score":0.995227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01597930559324296,"score_gpt":0.2653055751935859,"score_spread":0.249326269600343,"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."}}