{"id":"W4412860472","doi":"10.1016/j.media.2025.103715","title":"Attend-and-Refine: Interactive keypoint estimation and quantitative cervical vertebrae analysis for bone age assessment","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Korea Advanced Institute of Science and Technology; Ministry of Health and Welfare; Korea Health Industry Development Institute; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Ministry of Health and Family Welfare; Ministry of Food and Drug Safety; Ministry of Trade, Industry and Energy","keywords":"Computer science; Consistency (knowledge bases); Annotation; Process (computing); Artificial intelligence; Vertebra; Cervical vertebrae; Machine learning; Data mining; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000824844,0.001810953,0.001214789,0.002694883,0.0004745651,0.001139964,0.002176353,0.001809941,0.03713572],"category_scores_gemma":[0.002822054,0.001031507,0.001122529,0.00121098,0.0002599377,0.0009233892,0.002643585,0.0007807516,0.007968423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004040915,"about_ca_system_score_gemma":0.0008905419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008605246,"about_ca_topic_score_gemma":0.02355903,"domain_scores_codex":[0.9994662,0.00005543472,0.0000314316,0.0001205182,0.0002397999,0.00008649228],"domain_scores_gemma":[0.9993006,0.0003411502,0.00004269459,0.00009940573,0.00015106,0.00006518386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001050502,0.0001524244,0.003069163,0.0005169779,0.0002243459,0.0002614054,0.0003415001,0.006596335,0.06325658,0.001234554,0.0261055,0.8971907],"study_design_scores_gemma":[0.0003557485,0.0003602837,0.02010208,0.0001382866,0.0003111205,0.002063391,0.000401983,0.7667073,0.1399879,0.005765421,0.0635225,0.0002839739],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0148157,0.000733357,0.8986068,0.0001467585,0.00009859441,0.0003139876,0.002356209,0.08121376,0.001714762],"genre_scores_gemma":[0.09786162,0.0005162982,0.8864299,0.0001670112,0.00007402034,0.0003682284,0.002607077,0.00595221,0.006023556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03713572,"threshold_uncertainty_score":0.1242313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01162664375695198,"score_gpt":0.3571566181815153,"score_spread":0.3455299744245633,"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."}}