{"id":"W2071297770","doi":"10.1016/j.neuroimage.2006.09.016","title":"Segmentation of thalamic nuclei using a modified k-means clustering algorithm and high-resolution quantitative magnetic resonance imaging at 1.5 T","year":2006,"lang":"en","type":"article","venue":"NeuroImage","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":64,"is_retracted":false,"has_abstract":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Segmentation; Artificial intelligence; Magnetic resonance imaging; Computer science; Cluster analysis; Brain atlas; Similarity (geometry); Pattern recognition (psychology); Thalamus; Reproducibility; Euclidean distance; Surgical planning; Computer vision; Nuclear medicine; Medicine; Mathematics; Radiology; Image (mathematics)","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":[0.00007039101,0.0001516197,0.0002053299,0.0001157937,0.0001315843,0.00001637097,0.00005711065,0.00002728747,0.000009621314],"category_scores_gemma":[0.00001960074,0.0001605809,0.00004220705,0.0001969409,0.0001639463,0.0001504008,0.0000941875,0.0001233462,0.000001993111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006428882,"about_ca_system_score_gemma":0.00001461794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002480206,"about_ca_topic_score_gemma":0.000006597338,"domain_scores_codex":[0.9989336,0.00003865923,0.0002883987,0.0003631272,0.0001733699,0.0002029064],"domain_scores_gemma":[0.9994334,0.00005566164,0.0001413,0.0002567213,0.00007208707,0.00004085232],"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":[0.00008858637,0.0001089569,0.004171898,0.00007755184,0.000002433948,0.00005107466,0.00009112663,0.001123485,0.9640701,0.001102064,0.0001549828,0.02895771],"study_design_scores_gemma":[0.001270841,0.0001711749,0.108693,0.0001295727,0.00007704399,0.0002373839,0.00004976168,0.8592379,0.02832814,0.001275992,0.0003387566,0.0001904242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5787792,0.0008340919,0.4188098,0.0003417364,0.0000383429,0.0005273743,0.00005124523,0.0001585438,0.0004597049],"genre_scores_gemma":[0.6999454,0.00008350771,0.2995837,0.0001284294,0.00003376278,0.00001927154,0.00002611673,0.00003961162,0.0001401186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.935742,"threshold_uncertainty_score":0.6548299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04463760690121317,"score_gpt":0.3221354639266813,"score_spread":0.2774978570254681,"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."}}