{"id":"W3007455870","doi":"10.1186/s13244-019-0832-5","title":"Deep learning workflow in radiology: a primer","year":2020,"lang":"en","type":"review","venue":"Insights into Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":179,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Centre Intégré de Santé et de Services Sociaux des Laurentides; Université de Montréal; Université Laval; Cegep regional de Lanaudiere","funders":"Fonds de Recherche du Québec - Santé; Fondation de l'Association des radiologistes du Québec; Institut de Valorisation des Données","keywords":"Workflow; Neuroradiology; Medicine; Interventional radiology; Primer (cosmetics); Radiology; Medical physics; Computer science; Neurology; Database","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000427836,0.0006942483,0.002961073,0.0007831957,0.0001505911,0.00008946025,0.0003954405,0.0003081139,0.0001109218],"category_scores_gemma":[0.001362374,0.0005392594,0.00057599,0.0008781602,0.0002598081,0.0001338423,0.0002421814,0.004298551,0.0002679154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004801684,"about_ca_system_score_gemma":0.0004326033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009474809,"about_ca_topic_score_gemma":0.000004477831,"domain_scores_codex":[0.9964503,0.0004743408,0.001080477,0.0009852598,0.0003853229,0.00062428],"domain_scores_gemma":[0.9982681,0.0004207801,0.0003938479,0.0004547909,0.00005779069,0.0004046539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000115075,0.00004165499,0.0004651099,0.004530748,0.0001477101,0.002330753,0.000912305,0.00001944265,0.000004427436,0.000117862,0.0002799533,0.9911385],"study_design_scores_gemma":[0.0006439958,0.00004408663,0.00002481742,0.0164805,0.0005928837,0.0009585823,0.00004221235,0.01704873,6.021216e-7,0.0002313822,0.9634386,0.0004936488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001051845,0.9897475,0.003214747,0.001042506,0.000582289,0.0006983789,1.984174e-7,0.0002432866,0.004460586],"genre_scores_gemma":[0.000196535,0.9899898,0.00714571,0.0009732075,0.0009850592,0.00008511807,0.0001062082,0.0001968336,0.0003215016],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9906449,"threshold_uncertainty_score":0.9997059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01875206941140932,"score_gpt":0.3295022001419946,"score_spread":0.3107501307305853,"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."}}