{"id":"W4412727506","doi":"10.3390/diagnostics15141808","title":"Exploration of 3D Few-Shot Learning Techniques for Classification of Knee Joint Injuries on MR Images","year":2025,"lang":"en","type":"article","venue":"Diagnostics","topic":"Orthopedic Infections and Treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Taipei Medical University","keywords":"Artificial intelligence; Discriminative model; Machine learning; Computer science; Magnetic resonance imaging; Knee Joint; Medical imaging; Deep learning; Pattern recognition (psychology); Medicine; Radiology; Surgery","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":[0.0001067273,0.00007127924,0.0001720388,0.0001699469,0.00005348693,0.00000524118,0.00001219342,0.00005877834,0.000008938284],"category_scores_gemma":[0.001208544,0.00006154698,0.0000485751,0.0001347153,0.00005122583,0.00005983737,0.00001073502,0.00006841955,0.000002045233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003411608,"about_ca_system_score_gemma":0.00005391191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001723452,"about_ca_topic_score_gemma":0.000003304815,"domain_scores_codex":[0.9994923,0.00001858758,0.0002347641,0.00009992666,0.00008619161,0.00006817357],"domain_scores_gemma":[0.9991935,0.0002942793,0.0001228185,0.0001321816,0.0002410158,0.00001615221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004958209,0.003022643,0.6195437,0.001490189,0.000461316,0.000006039876,0.001043346,0.00007820847,0.0464385,0.04236651,0.00703854,0.2780152],"study_design_scores_gemma":[0.001294992,0.003113996,0.2473422,0.001025641,0.0005005842,0.000001110425,0.0004875412,0.0002923061,0.7339774,0.001516751,0.01032714,0.000120336],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8661375,0.0004574763,0.1033186,0.001857246,0.0004863535,0.002576486,0.0001187172,0.0002249144,0.02482265],"genre_scores_gemma":[0.9938775,0.0004909131,0.004737943,0.00004452632,0.00004109731,0.0001677709,0.0001156519,0.00000896375,0.000515657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6875389,"threshold_uncertainty_score":0.2509813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04725397052951801,"score_gpt":0.342070525256944,"score_spread":0.294816554727426,"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."}}