{"id":"W2593009668","doi":"10.1016/j.neuroimage.2017.02.069","title":"Evaluating accuracy of striatal, pallidal, and thalamic segmentation methods: Comparing automated approaches to manual delineation","year":2017,"lang":"en","type":"article","venue":"NeuroImage","topic":"Neurological disorders and treatments","field":"Medicine","cited_by":82,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Raymond and Beverly Sackler Foundation","keywords":"Globus pallidus; Basal ganglia; Thalamus; Striatum; Neuroimaging; Gold standard (test); Neuroscience; Segmentation; Psychology; Nuclear medicine; Pattern recognition (psychology); Artificial intelligence; Medicine; Computer science; Radiology; Central nervous system","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":[0.0002400299,0.0001149645,0.000239952,0.00005252282,0.0001575382,0.00006277893,0.00008041475,0.00003480982,0.00001178742],"category_scores_gemma":[0.0008099602,0.00009311194,0.00003631622,0.00004265832,0.00004694494,0.0001491117,0.0001020371,0.00008312329,0.000005161443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001011002,"about_ca_system_score_gemma":0.00001388736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004301493,"about_ca_topic_score_gemma":0.000003619504,"domain_scores_codex":[0.9990798,0.0001152706,0.0002314531,0.0002791072,0.000166322,0.0001280508],"domain_scores_gemma":[0.9992463,0.0001441668,0.0002040015,0.0003014915,0.00003831704,0.00006574117],"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":[0.0006167952,0.0005654935,0.3159873,0.0002398652,0.0001070321,0.0000407765,0.0004525933,0.0003832197,0.3598463,0.0001008062,0.0001804117,0.3214794],"study_design_scores_gemma":[0.002540609,0.0007762996,0.8576249,0.00003887917,0.0001500434,0.000006820314,0.00008389873,0.1150675,0.02342173,0.0001857499,0.00001228389,0.00009125925],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995515,0.0000395386,0.002626702,0.000608387,0.00004688963,0.00060317,0.000006833446,0.00008080623,0.0004727128],"genre_scores_gemma":[0.9616833,0.0000206458,0.03798153,0.0001925373,0.00001830913,0.00002130382,0.00003096221,0.00001245504,0.00003891254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5416376,"threshold_uncertainty_score":0.3796995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4165191632829157,"score_gpt":0.4866087605635777,"score_spread":0.07008959728066194,"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."}}