{"id":"W2604915122","doi":"10.1016/j.neuroimage.2017.04.018","title":"A comparison of accurate automatic hippocampal segmentation methods","year":2017,"lang":"en","type":"article","venue":"NeuroImage","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute on Aging; Fonds de recherche du Québec – Nature et technologies; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Fujirebio Europe; Eisai; Canada Foundation for Innovation; U.S. Department of Defense; Eli Lilly and Company; Compute Canada; Lundbeckfonden; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Northern California Institute for Research and Education; Roche; McGill University; Natural Sciences and Engineering Research Council of Canada; Pfizer; Biogen; BioClinica; University of Southern California; Bristol-Myers Squibb; Solve ME/CFS Initiative; Novartis Pharmaceuticals Corporation; Merck; Alzheimer's Drug Discovery Foundation; IXICO; Takeda Pharmaceutical Company; AbbVie; Alzheimer's Association; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Segmentation; Artificial intelligence; Hippocampal formation; Pattern recognition (psychology); Computer science; Fully automatic; Cognitive impairment; Automated method; Cognition; Psychology; Neuroscience","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006683652,0.002212264,0.002448626,0.00589617,0.001185244,0.004229645,0.003261964,0.003376672,0.005078757],"category_scores_gemma":[0.02009636,0.001200279,0.001905608,0.003212843,0.0007268365,0.003042232,0.001879521,0.001515252,0.002246036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00174823,"about_ca_system_score_gemma":0.003218762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01645185,"about_ca_topic_score_gemma":0.0275873,"domain_scores_codex":[0.9956595,0.0008703385,0.0004663767,0.0008355182,0.00179765,0.0003705103],"domain_scores_gemma":[0.9857868,0.007523022,0.0006513335,0.001613063,0.00412262,0.0003031258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005064463,0.0004709899,0.01004423,0.001738553,0.002064328,0.0002715652,0.0004899456,0.06252955,0.02016938,0.00423899,0.01543954,0.8774785],"study_design_scores_gemma":[0.0007429781,0.001029983,0.02945928,0.0003690573,0.001162786,0.00224562,0.000631638,0.8971336,0.04432815,0.008980301,0.01361656,0.0002999754],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3026769,0.0287922,0.6304241,0.001874248,0.002451613,0.0006727789,0.005265973,0.01846682,0.009375355],"genre_scores_gemma":[0.4817607,0.006767377,0.4865983,0.0006406606,0.0004249255,0.0002620686,0.0114764,0.004452069,0.007617544],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01645185,"threshold_uncertainty_score":0.03534693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1404364286662512,"score_gpt":0.5056442757020695,"score_spread":0.3652078470358183,"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."}}