{"id":"W341325887","doi":"10.1016/j.nicl.2015.05.001","title":"Rotation-invariant multi-contrast non-local means for MS lesion segmentation","year":2015,"lang":"en","type":"article","venue":"NeuroImage Clinical","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"Ministerio de Economía y Competitividad; Agence Nationale de la Recherche; Canadian Institutes of Health Research; Multiple Sclerosis Society; Multiple Sclerosis Society of Canada","keywords":"Segmentation; Invariant (physics); Contrast (vision); Lesion; Physics; Rotation (mathematics); Nuclear magnetic resonance; Artificial intelligence; Pattern recognition (psychology); Neuroscience; Psychology; Medicine; Computer science; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.001549368,0.0001967483,0.0004911213,0.00008822286,0.0001301083,0.00004319365,0.0001362198,0.0001318445,0.00002672694],"category_scores_gemma":[0.007935658,0.0001616624,0.0002382087,0.00014576,0.0003101549,0.0001599286,0.000103778,0.0003928583,0.0001418848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001007715,"about_ca_system_score_gemma":0.0002726999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005992196,"about_ca_topic_score_gemma":0.00007269097,"domain_scores_codex":[0.9974285,0.0002276702,0.0007832504,0.0005932157,0.0005647654,0.0004026231],"domain_scores_gemma":[0.9971431,0.001238071,0.0001441553,0.0003906484,0.0005857563,0.0004982215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01028914,0.007645985,0.2300966,0.0005943528,0.0005988272,0.0004143769,0.002549039,0.0005369305,0.1384859,0.0001303473,0.1440668,0.4645917],"study_design_scores_gemma":[0.03032032,0.003034306,0.7340548,0.0001286248,0.0001862157,0.0000233625,0.0008393675,0.221049,0.004352087,0.0000418858,0.005662876,0.0003071743],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3946601,0.00007872585,0.58987,0.007833087,0.00137667,0.004425229,0.0001024009,0.0002254564,0.001428288],"genre_scores_gemma":[0.9517839,0.000217217,0.04437183,0.001676799,0.0008812541,0.0002658346,0.0001277179,0.00006078382,0.0006146422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5571238,"threshold_uncertainty_score":0.9500297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2968536514325432,"score_gpt":0.4662086661791762,"score_spread":0.169355014746633,"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."}}