{"id":"W4224209800","doi":"10.1080/21681163.2022.2068160","title":"Fast and robust femur segmentation from computed tomography images for patient-specific hip fracture risk screening","year":2022,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Icelandic Centre for Research","keywords":"Osteoporosis; Segmentation; Femur; Ground truth; Hip fracture; Computed tomography; Medicine; Fracture (geology); Radiology; Artificial intelligence; Computer science; Geology; Surgery; Internal 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001068828,0.0002119275,0.0003402552,0.0007612621,0.0002478687,0.00008951676,0.00008562925,0.00008644572,0.00001939373],"category_scores_gemma":[0.00006632767,0.0002091547,0.00005935645,0.0008332796,0.00005033045,0.00009634673,0.0002301641,0.0003588235,1.384222e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007221494,"about_ca_system_score_gemma":0.00003041695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007605436,"about_ca_topic_score_gemma":2.842214e-7,"domain_scores_codex":[0.9980657,0.0002331987,0.0004557174,0.0005125369,0.0003720296,0.000360844],"domain_scores_gemma":[0.9989781,0.0003868132,0.000133592,0.0001533104,0.00008849428,0.0002596889],"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":[0.0001259302,0.0001771538,0.002250727,0.0002488787,0.00004733124,0.00001413356,0.0005936535,0.001377913,0.04296648,0.00008338993,0.0005788403,0.9515356],"study_design_scores_gemma":[0.001891853,0.0003902328,0.004835539,0.0001338323,0.00003082255,0.00003022544,0.000203862,0.9804127,0.002662917,0.0001368329,0.009058161,0.0002130803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01896095,0.002546957,0.9767712,0.0003955534,0.0004664474,0.0006583616,0.00008928293,0.0001106645,6.050768e-7],"genre_scores_gemma":[0.06539614,0.0003257131,0.9323207,0.0006057391,0.0002154555,0.0001013217,0.0009825389,0.00005022104,0.000002235822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9790347,"threshold_uncertainty_score":0.8529083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02267552850101493,"score_gpt":0.3419508040416513,"score_spread":0.3192752755406364,"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."}}