{"id":"W3097180705","doi":"10.1049/el.2020.2102","title":"Brain MRI‐based Wilson disease tissue classification: an optimised deep transfer learning approach","year":2020,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Trace Elements in Health","field":"Nursing","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Transfer of learning; Artificial intelligence; White matter; Hyperintensity; Random forest; Receiver operating characteristic; Computer science; Magnetic resonance imaging; Classifier (UML); Pattern recognition (psychology); Deep learning; Machine learning; Medicine; Radiology","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":[0.0009592006,0.0008735629,0.0006056634,0.0007052321,0.0002828165,0.0007259265,0.001316153,0.001262094,0.001841896],"category_scores_gemma":[0.001299258,0.0003098566,0.0006735098,0.0004433767,0.000324254,0.000641872,0.0006389235,0.001026674,0.0008069682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008740111,"about_ca_system_score_gemma":0.0009938177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006571645,"about_ca_topic_score_gemma":0.006022488,"domain_scores_codex":[0.9997237,0.00006633953,0.00001600594,0.00007598724,0.00005791918,0.00006007441],"domain_scores_gemma":[0.9996239,0.000139132,0.00003384447,0.00003387827,0.0001422259,0.00002693984],"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":[0.0004763032,0.0003101384,0.002650484,0.00009717358,0.0001149424,0.0002058786,0.00008876745,0.4383464,0.01616502,0.001699786,0.005080652,0.5347646],"study_design_scores_gemma":[0.000009856347,0.0000683334,0.0002370711,0.000005083503,0.000009446044,0.00002814893,0.00001354337,0.9961854,0.002271497,0.0008384029,0.0003288874,0.000004449871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1899288,0.001108858,0.7988737,0.0007895751,0.0001412751,0.0001689123,0.0002476609,0.004269927,0.004471343],"genre_scores_gemma":[0.8154144,0.0002551519,0.1753485,0.0004209859,0.00006158093,0.0001185004,0.0006380186,0.0001208141,0.007621834],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006571645,"threshold_uncertainty_score":0.01306683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02696956418752131,"score_gpt":0.2860499704508784,"score_spread":0.259080406263357,"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."}}