{"id":"W3106706388","doi":"10.1109/tip.2020.3038363","title":"PWD-3DNet: A Deep Learning-Based Fully-Automated Segmentation of Multiple Structures on Temporal Bone CT Scans","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Facial Nerve Paralysis Treatment and Research","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Artificial intelligence; Computer science; Temporal bone; Computer vision; Voxel; Image segmentation; Smoothing; Pattern recognition (psychology); Anatomy","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":[0.00009186727,0.0002213245,0.0003591783,0.0002688021,0.0002820975,0.00005624615,0.00006906721,0.00006254734,0.0001873617],"category_scores_gemma":[0.00003565004,0.0001813796,0.0001587291,0.0006835834,0.0001377422,0.0001542352,9.679173e-7,0.0003760582,0.00003489635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008191592,"about_ca_system_score_gemma":0.0001580567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009303778,"about_ca_topic_score_gemma":0.00003531261,"domain_scores_codex":[0.9984529,0.00009378815,0.0003470455,0.0003469003,0.000500069,0.0002592726],"domain_scores_gemma":[0.9993049,0.00007115367,0.0001377542,0.0001283979,0.0001800397,0.0001777357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004010132,0.001530973,0.003931072,0.001344415,0.0003247482,0.0002038037,0.001865013,0.1619589,0.6372944,6.432551e-7,0.0001136548,0.1874223],"study_design_scores_gemma":[0.003549835,0.001014072,0.0009802475,0.0001611193,0.0001932129,0.000008976242,0.0003877128,0.4340368,0.5594703,0.000002729875,0.00003871309,0.0001562768],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.686144,0.0002179876,0.3104397,0.001597101,0.00007120355,0.0007118795,0.00003527043,0.0005550517,0.0002278117],"genre_scores_gemma":[0.9944372,0.00001117917,0.005012206,0.0002070955,0.00003710974,0.00004312917,0.00007054936,0.00004028863,0.0001412123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3082933,"threshold_uncertainty_score":0.7396443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02639964669233431,"score_gpt":0.3180663458364368,"score_spread":0.2916666991441025,"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."}}