{"id":"W4399846677","doi":"10.1016/j.compbiomed.2024.108791","title":"Deep learning-based automated detection and segmentation of bone and traumatic bone marrow lesions from MRI following an acute ACL tear","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Texas Academy of Science; Arthritis Society","keywords":"Bone marrow; Medicine; Segmentation; Magnetic resonance imaging; Radiology; Artificial intelligence; Computer science; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001209831,0.0008618375,0.0006902652,0.0008886039,0.0003006651,0.0007300343,0.001146726,0.001173314,0.0006980354],"category_scores_gemma":[0.00188057,0.0004020255,0.0008856825,0.0004782759,0.0003761298,0.0004895409,0.000724427,0.0007670964,0.0004489181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009066971,"about_ca_system_score_gemma":0.001060459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01220848,"about_ca_topic_score_gemma":0.01469786,"domain_scores_codex":[0.9996449,0.00007219423,0.00003076147,0.0001323657,0.0000579513,0.0000618496],"domain_scores_gemma":[0.999456,0.0002025826,0.00007781765,0.00004505596,0.0001830857,0.00003539182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0008859027,0.0004945046,0.01262593,0.0001948621,0.0002229828,0.0004120974,0.0001639831,0.5646465,0.03078349,0.0005545738,0.002912041,0.3861031],"study_design_scores_gemma":[0.000006942492,0.00008749095,0.001589605,0.00001543691,0.00002232112,0.00006031537,0.00001798447,0.9919567,0.005717393,0.0002771004,0.0002403514,0.00000827594],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5962211,0.001793145,0.3933144,0.0005052122,0.0001411118,0.0002493211,0.0007648379,0.004612182,0.002398873],"genre_scores_gemma":[0.9127098,0.0003294458,0.08207195,0.0003252091,0.00003632184,0.0001549548,0.001485875,0.00007425062,0.002812206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01220848,"threshold_uncertainty_score":0.02427489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01282748963088255,"score_gpt":0.304421951483377,"score_spread":0.2915944618524944,"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."}}