{"id":"W3049224424","doi":"10.1016/j.compmedimag.2020.101776","title":"Deep learning method for localization and segmentation of abdominal CT","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Simon Fraser University","funders":"National Cancer Institute","keywords":"Jaccard index; Segmentation; Convolutional neural network; Adipose tissue; Computer science; Lumbar; Artificial intelligence; Lumbar vertebrae; Pattern recognition (psychology); Medicine; Nuclear medicine; Anatomy","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":[0.0004440292,0.00008708644,0.0002305618,0.0000740591,0.00006984107,0.00001651221,0.00003497317,0.00003053631,0.00000661866],"category_scores_gemma":[0.0002139898,0.00008015428,0.00004056783,0.0001327862,0.0001205298,0.00005077181,0.00003615196,0.0001481459,9.58371e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006088999,"about_ca_system_score_gemma":0.00002313635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005397611,"about_ca_topic_score_gemma":2.337181e-7,"domain_scores_codex":[0.9991434,0.00008170335,0.0002295821,0.0001850868,0.0002649424,0.00009530697],"domain_scores_gemma":[0.9994243,0.0001340374,0.00008120743,0.00004855256,0.0001166767,0.0001951917],"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":[0.0005583726,0.0001209515,0.02407269,0.001699889,0.0001289632,0.00004134014,0.0009918223,0.00002446116,0.09117741,0.002337553,0.0008660103,0.8779805],"study_design_scores_gemma":[0.002481475,0.0002256809,0.001203072,0.0002408644,0.0001122392,0.00009729064,0.0000666597,0.9869928,0.00597297,0.0004356631,0.002085378,0.0000859577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00832788,0.000503971,0.9865621,0.004174644,0.00003845812,0.0002660896,8.38128e-7,0.0001053043,0.00002066527],"genre_scores_gemma":[0.5812315,0.0004326833,0.4132649,0.00483092,0.0001353181,0.00001754705,0.00006661139,0.00001820695,0.000002300899],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9869683,"threshold_uncertainty_score":0.3268597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254913733744719,"score_gpt":0.3235346784254246,"score_spread":0.3009855410879774,"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."}}