{"id":"W3081756191","doi":"10.1109/embc44109.2020.9176173","title":"Metal Artifacts Reduction in CT Scans using Convolutional Neural Network with Ground Truth Elimination","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Convolutional neural network; Streak; Computer science; Artificial intelligence; Ground truth; Computer vision; Image quality; Deep learning; Artifact (error); Reduction (mathematics); Pattern recognition (psychology); Image (mathematics); Geology","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":[0.0000452416,0.0001046855,0.000104613,0.00003561349,0.00005156245,0.00002166702,0.00003719537,0.00001569011,0.00003763449],"category_scores_gemma":[0.000009701736,0.0001001851,0.00001850133,0.0003136173,0.00002597251,0.0004933436,0.000008735206,0.0001347455,0.000005392139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007724405,"about_ca_system_score_gemma":0.00001371766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001841698,"about_ca_topic_score_gemma":0.0000132262,"domain_scores_codex":[0.9993969,0.00001456799,0.000138728,0.000134792,0.0001123309,0.0002027343],"domain_scores_gemma":[0.9998378,0.00001756629,0.00002071351,0.00004912213,0.00001982622,0.00005501121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001962189,0.000005588718,0.0003614488,0.00001255191,0.00001172958,0.000007262039,0.000113394,0.9923968,0.003827731,0.001269493,0.00001735648,0.001957043],"study_design_scores_gemma":[0.0003345149,0.00002826469,0.00564341,0.00001954684,0.00001835622,0.00005898316,0.0003724464,0.9907438,0.002246854,0.000259307,0.0001067949,0.0001677159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8717097,0.000116706,0.1266358,0.0001767425,0.0002354807,0.00009250065,0.000001130761,0.0001833812,0.0008485898],"genre_scores_gemma":[0.9947965,0.000004529994,0.004852934,0.00005241376,0.0002435942,0.000004388817,0.00001416167,0.00001876021,0.00001278581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1230867,"threshold_uncertainty_score":0.4085431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02311827934937498,"score_gpt":0.2200895233081459,"score_spread":0.1969712439587709,"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."}}