{"id":"W4207075585","doi":"10.1049/sil2.12101","title":"Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes","year":2022,"lang":"en","type":"article","venue":"IET Signal Processing","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Lesion; Magnetic resonance imaging; Perfusion; Fluid-attenuated inversion recovery; Medicine; Segmentation; Multiple sclerosis; Pattern recognition (psychology); Hyperintensity; Artificial intelligence; Radiology; Computer science; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.000423625,0.00009944247,0.0001321415,0.0002247696,0.0004137706,0.0000396729,0.0002031097,0.0000373314,0.0002586084],"category_scores_gemma":[0.0001283824,0.0001027842,0.00004106488,0.0008501286,0.00007423645,0.0002373838,0.00006770703,0.0002248616,0.00001202504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001334477,"about_ca_system_score_gemma":0.00008766934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001799546,"about_ca_topic_score_gemma":0.000008219899,"domain_scores_codex":[0.9984424,0.0002562321,0.0003530318,0.0003475209,0.0004350548,0.0001658324],"domain_scores_gemma":[0.9993508,0.0001542965,0.0002793696,0.0001419863,0.00003670309,0.00003680192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003475147,0.0001432211,0.00152463,0.00005166822,2.830432e-7,8.742281e-7,0.0006030085,0.000678303,0.9108883,0.00007861289,0.0000474171,0.08594891],"study_design_scores_gemma":[0.000457508,0.00008690731,0.07268651,0.00008095636,0.000004888386,0.000009634925,0.001012345,0.5429037,0.3820617,0.0002793149,0.0002790782,0.0001375046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956069,0.00005174696,0.00275905,0.0005625417,0.00008669868,0.000220023,0.000005313002,0.0001107172,0.0005970233],"genre_scores_gemma":[0.9994504,0.00001060519,0.0002018024,0.0001401338,0.00001594098,0.00007304016,0.000004628312,0.00001706519,0.00008640971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5422253,"threshold_uncertainty_score":0.4191419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09418724323760255,"score_gpt":0.2799455117324607,"score_spread":0.1857582684948582,"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."}}