{"id":"W2805515969","doi":"10.1007/s11548-018-1776-9","title":"A deep learning framework for segmentation and pose estimation of pedicle screw implants based on C-arm fluoroscopy","year":2018,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Spinal Fractures and Fixation Techniques","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"Surgical Specialties (Canada); Alberta Bone and Joint Health Institute; University of Calgary; BC Research (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Segmentation; Computer science; Artificial intelligence; Pose; Fluoroscopy; Convolutional neural network; Deep learning; Radiography; Computer vision; Medicine; Surgery","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":[0.000404288,0.00007337724,0.0002437703,0.0002790371,0.00004706914,0.00001584875,0.00004122251,0.00009757151,0.00002376551],"category_scores_gemma":[0.0002321294,0.00005873029,0.00007517222,0.00004252569,0.00008616113,0.00007425131,0.000009034548,0.0001422843,2.573145e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000250169,"about_ca_system_score_gemma":0.00004296758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000197791,"about_ca_topic_score_gemma":2.253888e-7,"domain_scores_codex":[0.9992676,0.0000589567,0.0003533617,0.00009031705,0.0001579674,0.00007180497],"domain_scores_gemma":[0.998391,0.0007818053,0.0003818376,0.00004086674,0.000351223,0.00005327622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007795322,0.0003780108,0.1364668,0.0001167873,0.0005433128,0.00008495834,0.0004850993,0.0008655884,0.00388741,0.001472045,0.002037737,0.8458669],"study_design_scores_gemma":[0.002478069,0.005270537,0.6891673,0.001195547,0.0001553886,0.003498366,0.00006408041,0.2790572,0.01409188,0.004173228,0.0006609867,0.0001874168],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4327119,0.0001171569,0.565993,0.0006911491,0.0004054267,0.00005926561,0.00000194317,0.000008060637,0.00001216635],"genre_scores_gemma":[0.9031411,0.00007049506,0.09531394,0.0009131637,0.0005282101,0.000002254707,0.00002230402,0.000005807585,0.000002700647],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8456795,"threshold_uncertainty_score":0.2394951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01907815153476481,"score_gpt":0.3383596774351396,"score_spread":0.3192815259003748,"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."}}