{"id":"W2098684027","doi":"10.1016/j.neuroimage.2009.02.013","title":"Automatic segmentation of the hippocampus and the amygdala driven by hybrid constraints: Method and validation","year":2009,"lang":"en","type":"article","venue":"NeuroImage","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":187,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Wellcome Trust","keywords":"Segmentation; Hippocampal sclerosis; Cohort; Artificial intelligence; Pattern recognition (psychology); Probabilistic logic; Computer science; Atlas (anatomy); Amygdala; Medicine; Nuclear medicine; Epilepsy; Temporal lobe; Neuroscience; Pathology; Internal medicine; Psychology; Anatomy","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":[],"consensus_categories":[],"category_scores_codex":[0.0002370355,0.00006954718,0.0001355921,0.00002257776,0.00006738817,0.00002135332,0.00003847322,0.00001360303,0.00003264167],"category_scores_gemma":[0.0001599843,0.00003576863,0.00003204618,0.00006107055,0.0002558539,0.00005019094,0.00001939255,0.00009260902,0.000001675416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001206918,"about_ca_system_score_gemma":0.00002373821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008949657,"about_ca_topic_score_gemma":4.333414e-7,"domain_scores_codex":[0.9992285,0.0002327849,0.0001315009,0.0001256931,0.0001849109,0.00009659246],"domain_scores_gemma":[0.9994732,0.0002187216,0.00006513092,0.0001618706,0.00003132953,0.00004970662],"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":[0.0001818414,0.0002103942,0.02469695,0.0001015825,0.00008391197,0.00003144544,0.00062641,0.000002300593,0.1331708,0.0003796411,0.001976845,0.8385379],"study_design_scores_gemma":[0.01719849,0.00143087,0.7748089,0.0001856092,0.0005258403,0.0006683946,0.0003377221,0.01142682,0.1744443,0.01865946,0.0001428878,0.0001706406],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920622,0.0001551315,0.0005829413,0.005719334,0.00001990034,0.0006283665,0.00001497325,0.00001614261,0.0008010547],"genre_scores_gemma":[0.9978734,0.0001159345,0.001400727,0.0005138018,0.00001011442,0.000009810532,0.00001180608,0.000004724529,0.00005966706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8383672,"threshold_uncertainty_score":0.1458602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397957974705237,"score_gpt":0.3106358260953877,"score_spread":0.2966562463483353,"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."}}