{"id":"W2358693203","doi":"10.1080/10255842.2016.1181173","title":"Interactive graph-cut segmentation for fast creation of finite element models from clinical ct data for hip fracture prediction","year":2016,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics & Biomedical Engineering","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"National Institute on Aging; National Institutes of Health","keywords":"Segmentation; Finite element method; Graph; Hip fracture; Computer science; Fracture (geology); Artificial intelligence; Geology; Structural engineering; Medicine; Theoretical computer science; Engineering; Geotechnical engineering","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":[0.002782735,0.0002391093,0.0006010318,0.0004474004,0.00003629176,0.00002027854,0.0003413919,0.000180763,0.00001753406],"category_scores_gemma":[0.001345984,0.0001790638,0.0001737119,0.0003038551,0.00007122329,0.0002341228,0.0001968032,0.0003196661,5.260969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001305531,"about_ca_system_score_gemma":0.00007581746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002245099,"about_ca_topic_score_gemma":5.045609e-7,"domain_scores_codex":[0.9975107,0.0001458358,0.001043722,0.0006553739,0.000319801,0.0003245715],"domain_scores_gemma":[0.9958005,0.003037734,0.0002770098,0.0005317435,0.0001270986,0.0002258961],"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":[0.0002656627,0.0002960112,0.00007878325,0.0002337538,0.0002995883,0.000005206449,0.0001652513,0.00159771,0.1005195,0.0002915479,0.0007371978,0.8955098],"study_design_scores_gemma":[0.003946441,0.0005315474,0.0001162161,0.0007469268,0.0001519298,0.00000705274,0.00002754495,0.9723359,0.00840418,0.003780058,0.009784665,0.0001675776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00356892,0.0001268849,0.9918001,0.001227569,0.001774025,0.0009295465,0.0004831394,0.00008720735,0.000002645277],"genre_scores_gemma":[0.05880829,0.0002019847,0.9380815,0.0003290791,0.0008727442,0.0001053239,0.001541509,0.00005104037,0.000008503444],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9707382,"threshold_uncertainty_score":0.7302011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0509533755087771,"score_gpt":0.4094892290350451,"score_spread":0.358535853526268,"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."}}