{"id":"W4390230077","doi":"10.1080/21681163.2023.2296626","title":"A CNN-based strategy to automate contour detection of the hip and proximal femur using DXA hip images from longitudinal databases (CLSA and CaMos)","year":2023,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"Hip and Femur Fractures","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Pfizer Canada; Novartis Pharmaceuticals Canada; Arthritis Society; Government of Canada; Dairy Farmers of Canada; Sanofi; Amgen Canada; Eli Lilly Canada; Servier; Amgen; Pfizer; Eli Lilly and Company","keywords":"Artificial intelligence; Computer science; Femur; Intersection (aeronautics); Convolutional neural network; Image processing; Pelvis; Computer vision; Pattern recognition (psychology); Image (mathematics); Medicine; Radiology; Surgery; Cartography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007446196,0.0001933949,0.0003123603,0.0004626228,0.00007678363,0.00005806227,0.0000691855,0.0000811164,0.000003027841],"category_scores_gemma":[0.0002064632,0.0001494056,0.00003222459,0.0007976,0.00008395311,0.00008411663,0.0001592542,0.0001217955,1.930743e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003764854,"about_ca_system_score_gemma":0.00004517835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002423642,"about_ca_topic_score_gemma":0.000002366186,"domain_scores_codex":[0.9987237,0.0001142555,0.0003330726,0.0003711773,0.0002201636,0.0002375791],"domain_scores_gemma":[0.9993105,0.0002235817,0.00008496233,0.000163842,0.00006273117,0.0001543652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004016845,0.00005121995,0.002251096,0.0003476099,0.00003283159,0.00002106329,0.0002264373,0.0003302703,0.8684669,0.00009716181,0.00001449826,0.1281207],"study_design_scores_gemma":[0.0007016814,0.0001122194,0.02309713,0.0004395717,0.0000571205,0.00002545671,0.00003879704,0.9050237,0.07010791,0.0001010446,0.0001472114,0.0001481985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3958464,0.0002506413,0.6032686,0.0001265366,0.0002134612,0.000196135,0.0000208029,0.00007711588,3.043327e-7],"genre_scores_gemma":[0.8960201,0.00003719988,0.1036093,0.0001259062,0.0001279003,0.00000876075,0.00004383725,0.00002558057,0.000001421737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9046934,"threshold_uncertainty_score":0.6092586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0442889233229953,"score_gpt":0.3767044340495469,"score_spread":0.3324155107265516,"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."}}