{"id":"W2069577302","doi":"10.1002/jmri.22004","title":"Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T","year":2010,"lang":"en","type":"article","venue":"Journal of Magnetic Resonance Imaging","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Fluid-attenuated inversion recovery; Hyperintensity; Voxel; Thresholding; Segmentation; Pattern recognition (psychology); Computer science; Artificial intelligence; Magnetic resonance imaging; Medicine; Radiology","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":[0.0006158279,0.0001239319,0.0002218976,0.0001779355,0.0001786321,0.00005152325,0.0002466337,0.0000193647,0.0001770719],"category_scores_gemma":[0.001424651,0.00008928986,0.00008276767,0.0002220458,0.0002688351,0.000394441,0.00009625156,0.0003083405,0.000007505887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005318466,"about_ca_system_score_gemma":0.00004194524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000200515,"about_ca_topic_score_gemma":0.00001898407,"domain_scores_codex":[0.9985476,0.0001660864,0.0004606872,0.000161203,0.000469794,0.0001946605],"domain_scores_gemma":[0.9978401,0.001461177,0.0003546283,0.0001792687,0.0001418121,0.0000230156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005572688,0.00005975157,0.1369334,0.00005027009,0.000002299125,0.00009907933,0.002851959,0.0001041598,0.8326505,0.00003130488,0.002783767,0.02437782],"study_design_scores_gemma":[0.001119096,0.0003014177,0.8892703,0.000278896,0.00003866369,0.003229312,0.00288967,0.009671596,0.08930763,0.001040619,0.002613663,0.0002391306],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893937,0.0008590521,0.0001152819,0.00853084,0.0004676911,0.0001217032,0.000003633547,0.000006618349,0.0005015204],"genre_scores_gemma":[0.9951327,0.00003227424,0.002962977,0.001597639,0.00009550426,0.000003730092,8.478832e-8,0.00001277588,0.0001622707],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7523369,"threshold_uncertainty_score":0.3641135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01781597900507935,"score_gpt":0.261414729779363,"score_spread":0.2435987507742837,"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."}}