{"id":"W2953430427","doi":"10.1016/j.phro.2019.05.001","title":"Automatic recognition and analysis of metal streak artifacts in head and neck computed tomography for radiomics modeling","year":2019,"lang":"en","type":"article","venue":"Physics and Imaging in Radiation Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Streak; Radiomics; Artifact (error); Artificial intelligence; Receiver operating characteristic; Random forest; Computer science; Hough transform; Computed tomography; Test set; Pattern recognition (psychology); Data set; Computer vision; Radiology; Medicine; Machine learning; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00146102,0.0005709175,0.000437889,0.00157771,0.0002011397,0.0006851736,0.0006571978,0.000555078,0.00050697],"category_scores_gemma":[0.004291296,0.000216971,0.0006696758,0.0004950131,0.0003067492,0.0003503098,0.0003818683,0.0003879971,0.0003133989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003609317,"about_ca_system_score_gemma":0.0006840947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001721823,"about_ca_topic_score_gemma":0.002700414,"domain_scores_codex":[0.999124,0.0002351169,0.00006656748,0.0001620696,0.0003634456,0.00004891005],"domain_scores_gemma":[0.9978447,0.0008185606,0.0004118202,0.0002431367,0.0006312227,0.00005045221],"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":[0.0004641922,0.0002547654,0.06851947,0.0002476533,0.0002602907,0.0003266386,0.0001898445,0.1090617,0.1818398,0.0009145872,0.001916157,0.636005],"study_design_scores_gemma":[0.00003048678,0.0001969357,0.04628633,0.00002647909,0.00009129219,0.001242037,0.00003537969,0.840571,0.10856,0.0007300566,0.002184934,0.00004503502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2019085,0.0004908668,0.7951854,0.00007345584,0.00002438657,0.0001044012,0.0001529692,0.001603201,0.0004567317],"genre_scores_gemma":[0.6940582,0.000190391,0.3044082,0.00005478217,0.00003288769,0.0001020482,0.0004371285,0.0001479381,0.0005684546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001721823,"threshold_uncertainty_score":0.007726669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02045560587393682,"score_gpt":0.3167414912519355,"score_spread":0.2962858853779987,"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."}}