{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003504389,0.0003193429,0.0002716823,0.00009404185,0.0003523867,0.000117022,0.0004268207,0.0001035115,0.0001092539],"category_scores_gemma":[0.00008977432,0.000365416,0.00009317533,0.0004141185,0.00007821338,0.0003047452,0.00001287803,0.0009631514,0.00004039675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004273212,"about_ca_system_score_gemma":0.0001421699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000892039,"about_ca_topic_score_gemma":0.00001001128,"domain_scores_codex":[0.9968587,0.0004967149,0.0004027385,0.0007984298,0.0005034407,0.0009399458],"domain_scores_gemma":[0.9987588,0.0001205661,0.00008552801,0.0004363635,0.00003654469,0.0005621797],"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":[0.004564528,0.001113908,0.006059126,0.0009311839,0.000152066,0.00005891196,0.008740126,0.5083223,0.3778227,0.003621062,0.01977929,0.06883478],"study_design_scores_gemma":[0.004016349,0.001568592,0.004014931,0.00003789257,0.0001790559,0.000004377792,0.0002833246,0.8018357,0.01192523,0.00005938751,0.1749638,0.00111135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3463733,0.0006776091,0.3154229,0.3350815,0.0002647828,0.001210532,0.00001078801,0.0007459383,0.000212698],"genre_scores_gemma":[0.9453089,0.0000107466,0.008436975,0.04521007,0.0004598904,0.00009659142,0.0003313407,0.000123385,0.00002208652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5989357,"threshold_uncertainty_score":0.9998798,"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."}}