{"id":"W4281677693","doi":"10.1002/jmri.28284","title":"Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee <scp>MRI</scp>","year":2022,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Knee injuries and reconstruction techniques","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and Technology","keywords":"Receiver operating characteristic; Magnetic resonance imaging; Meniscus; Coronal plane; Computer science; Sagittal plane; Convolutional neural network; Artificial intelligence; Wilcoxon signed-rank test; Data set; Discriminative model; Mann–Whitney U test; Medicine; Radiology; Nuclear medicine; Machine learning; Mathematics; Statistics","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":[0.0006497552,0.0001543727,0.0004707577,0.0003871537,0.0002051137,0.00002268075,0.0001170127,0.00004161812,0.0002028791],"category_scores_gemma":[0.0001273474,0.0001339972,0.0002400582,0.0003256535,0.0001901617,0.0001315776,0.00006661815,0.0006674314,7.174123e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002492316,"about_ca_system_score_gemma":0.0001412802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001836658,"about_ca_topic_score_gemma":5.300985e-7,"domain_scores_codex":[0.9979627,0.0001299991,0.0008730949,0.0001575207,0.0006173917,0.0002593032],"domain_scores_gemma":[0.9985745,0.0001610411,0.0007718201,0.0001723009,0.0002200354,0.000100286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003504708,0.0003353001,0.0258764,0.0001501961,0.00006096052,0.000287022,0.0004018667,0.01041012,0.05459948,0.0001142838,0.003442539,0.9039714],"study_design_scores_gemma":[0.003411244,0.003575302,0.07653052,0.0005851109,0.0002911219,0.01620059,0.002015223,0.8655784,0.007336585,0.0005324738,0.02376832,0.000175092],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9824125,0.012192,0.003364473,0.0004250209,0.0009657904,0.0002421687,0.000006392207,0.00004176488,0.0003499407],"genre_scores_gemma":[0.99174,0.0001364689,0.007329156,0.0002085431,0.0003221002,0.000007507185,9.038833e-7,0.00002726848,0.0002280066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9037963,"threshold_uncertainty_score":0.5464247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008282651950181154,"score_gpt":0.2485307106829051,"score_spread":0.240248058732724,"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."}}