{"id":"W2912772276","doi":"10.29007/j56f","title":"A deep learning-based approach for localization of pedicle regions in preoperative CT scans","year":2018,"lang":"en","type":"article","venue":"EPiC series in health sciences","topic":"Spinal Fractures and Fixation Techniques","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital; University of Calgary; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Centre for Hip Health and Mobility; Institute for Computing, Information and Cognitive Systems","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Process (computing); Computed tomography; Computer vision; Fixation (population genetics); Ground truth; Surgical planning; Image registration; Radiology; Medicine; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008251527,0.00005906478,0.0001749426,0.0001878566,0.0001557376,0.000008198722,0.00007396154,0.0000274007,0.0000300273],"category_scores_gemma":[0.0004536292,0.00004621591,0.00001838981,0.0007234167,0.0005128479,0.0001122174,0.000009597801,0.00007853688,2.313135e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005919104,"about_ca_system_score_gemma":0.0003259706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007912962,"about_ca_topic_score_gemma":0.0005147667,"domain_scores_codex":[0.9991158,0.00006428268,0.0002976334,0.0001871517,0.0001601956,0.0001749786],"domain_scores_gemma":[0.9995812,0.00006363937,0.0001313539,0.0000812073,0.00009632875,0.00004624951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007199254,0.0004801878,0.9194323,0.001274791,0.000006507427,0.000002536738,0.0102464,0.03622716,0.00005367583,0.01962917,0.0006814759,0.0112459],"study_design_scores_gemma":[0.001597361,0.01278039,0.1051942,0.0006777747,0.000007889234,0.00002628463,0.009033199,0.8529772,0.006672701,0.002903054,0.007917599,0.000212312],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09616216,0.0007166665,0.8928149,0.005971271,0.0001360129,0.001874077,0.000003117317,0.00008434791,0.002237469],"genre_scores_gemma":[0.9786185,0.00005057481,0.02021673,0.0008796737,0.00005262079,0.00008201897,0.00001020737,0.000004180405,0.00008550403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8824564,"threshold_uncertainty_score":0.1889609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04195880438886145,"score_gpt":0.3752287986027437,"score_spread":0.3332699942138822,"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."}}