{"id":"W3039802208","doi":"10.1002/mp.14368","title":"Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"BC Cancer Foundation; Swiss Cancer Research Foundation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Repeatability; Magnetic resonance imaging; Glioblastoma; Image registration; Medical imaging; Medical physics; Nuclear medicine; Artificial intelligence; Medicine; Computer science; Radiology; Image (mathematics); Mathematics; Statistics","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":[0.0004197298,0.000128182,0.0005003247,0.00004595243,0.00002461967,0.00000612555,0.0001165206,0.00005673309,0.00004292665],"category_scores_gemma":[0.005623994,0.000111506,0.00007210757,0.0003869471,0.0009093796,0.00007708786,0.00006037911,0.0004893166,7.909046e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002286281,"about_ca_system_score_gemma":0.0001566014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000135093,"about_ca_topic_score_gemma":0.000004379114,"domain_scores_codex":[0.9984471,0.00006233481,0.0004723467,0.0003012777,0.0005457603,0.0001711548],"domain_scores_gemma":[0.998942,0.0003666836,0.000151487,0.0002283853,0.00007815433,0.0002332986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003070083,0.0004115035,0.8283207,0.001013198,0.0000159038,0.0002835266,0.001091446,0.000009694566,0.05576325,0.0001819948,0.001488791,0.1111129],"study_design_scores_gemma":[0.004116272,0.0008563952,0.882195,0.0008846953,0.0001597635,0.0001449624,0.0001458694,0.07438505,0.03511204,0.00151509,0.0002309491,0.0002539158],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9831032,0.004210376,0.003734287,0.007888733,0.00004030744,0.0002185395,0.00001090274,0.0000371221,0.0007565903],"genre_scores_gemma":[0.9975927,0.0001225498,0.001541009,0.0005383795,0.0001598642,0.000003286665,0.00001061721,0.00001528532,0.00001631873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.110859,"threshold_uncertainty_score":0.6732852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01246669645454345,"score_gpt":0.3059636792361384,"score_spread":0.293496982781595,"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."}}