{"id":"W2021204548","doi":"10.1016/j.media.2012.09.004","title":"Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging","year":2012,"lang":"en","type":"review","venue":"Medical Image Analysis","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":361,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Segmentation; Magnetic resonance imaging; Multiple sclerosis; Computer science; Artificial intelligence; Lesion; Image segmentation; Pattern recognition (psychology); Medicine; Radiology; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003620278,0.0004969876,0.004500386,0.001082648,0.0000857246,0.00001423066,0.0004084533,0.0001892059,0.0200858],"category_scores_gemma":[0.004261789,0.000354218,0.002366328,0.002522592,0.0006215023,0.0001087249,0.0002894812,0.0006295834,0.0001831795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001826791,"about_ca_system_score_gemma":0.0002933565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006680618,"about_ca_topic_score_gemma":0.00000732392,"domain_scores_codex":[0.992822,0.001703059,0.002297716,0.0005965073,0.002083006,0.0004977022],"domain_scores_gemma":[0.9951417,0.001928969,0.001007274,0.0009440706,0.0005469706,0.0004309988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000006669074,0.0003491657,0.003058843,0.1306936,0.001182929,0.000006070401,0.00002819902,5.982118e-8,0.00002409249,0.000001055624,0.004755515,0.8598938],"study_design_scores_gemma":[0.001597549,0.0001541251,0.04960625,0.5634264,0.0647881,0.00002441398,0.00006643233,0.002803223,0.00006105946,0.000003021574,0.316827,0.0006424405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005325012,0.9930235,0.004451665,0.0006411886,0.00006530002,0.001178253,0.0001807366,0.00002888864,0.0004252138],"genre_scores_gemma":[0.00002762937,0.9636894,0.03428182,0.0005744564,0.0001008918,0.0003587224,0.0005867062,0.0000532374,0.0003271308],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8592514,"threshold_uncertainty_score":0.999891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.130202479353036,"score_gpt":0.4478487463707702,"score_spread":0.3176462670177342,"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."}}