{"id":"W1991456242","doi":"10.1016/j.neuroimage.2010.04.193","title":"Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion","year":2010,"lang":"en","type":"article","venue":"NeuroImage","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Douglas Mental Health University Institute; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Segmentation; Artificial intelligence; Pattern recognition (psychology); Computer science; Amygdala; Template; Gold standard (test); Dice; Hippocampus; Fusion; Transformation (genetics); Atlas (anatomy); Set (abstract data type); Mathematics; Medicine; Neuroscience; Biology; Anatomy; 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":[0.0001144665,0.0001285609,0.0001315306,0.00004719977,0.0001115413,0.0002211128,0.0003498861,0.00004571215,0.00003985438],"category_scores_gemma":[0.0000374934,0.00008749282,0.0000146139,0.0002185089,0.0001636551,0.00143984,0.0004064586,0.0002142035,0.00000111589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003066459,"about_ca_system_score_gemma":0.00003653006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002298797,"about_ca_topic_score_gemma":0.000001835114,"domain_scores_codex":[0.9989266,0.0001027088,0.000225797,0.0003222903,0.0002801532,0.0001424645],"domain_scores_gemma":[0.999275,0.0001169799,0.0001969475,0.0003095546,0.00001937096,0.00008210813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008421027,0.00003497091,0.002567128,0.00003037488,0.00000568666,0.000007456166,0.0003526265,6.361845e-8,0.8657445,0.00005611755,0.0009015148,0.1302911],"study_design_scores_gemma":[0.001113886,0.0003227423,0.09648005,0.00009878125,0.00002530279,0.00004315689,0.00005597163,0.03036378,0.8691783,0.002039368,0.00006327194,0.0002154219],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9514982,0.00003526967,0.04659823,0.001027467,0.00008953983,0.0003020253,0.00001528961,0.000195867,0.0002381459],"genre_scores_gemma":[0.7736891,0.00004060643,0.2253611,0.0008172204,0.00001696474,0.00001621019,0.000008741769,0.00001556148,0.00003446577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1787629,"threshold_uncertainty_score":0.3567854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00907286689020323,"score_gpt":0.2452359640651315,"score_spread":0.2361630971749283,"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."}}