{"id":"W2884177016","doi":"10.1109/jbhi.2018.2857217","title":"Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease","year":2018,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; Solve ME/CFS Initiative; National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; U.S. Department of Defense","keywords":"Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Computer science; Majority rule; Neuroimaging; Positron emission tomography; Feature selection; Medicine; Nuclear medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006746678,0.00007747485,0.000199733,0.0001654544,0.0001783,0.00003246106,0.0001116082,0.00003812185,0.00001072472],"category_scores_gemma":[0.001003358,0.00005797651,0.00006142505,0.0001862175,0.0003216107,0.0003069141,0.0000135874,0.0001512161,0.000002004627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002481825,"about_ca_system_score_gemma":0.0001892926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003322545,"about_ca_topic_score_gemma":7.329091e-7,"domain_scores_codex":[0.998568,0.00005808812,0.0007931998,0.00006642636,0.0003510733,0.0001631984],"domain_scores_gemma":[0.9979967,0.0004115817,0.0009908912,0.00009372496,0.0001632152,0.0003439005],"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":[0.0006765506,0.0004760284,0.0006176449,0.001113296,0.00004240858,0.00001285641,0.006202629,0.00001062761,0.02494348,0.0007928615,0.2760938,0.6890178],"study_design_scores_gemma":[0.0136745,0.008397561,0.1058622,0.002342338,0.0002869901,0.001727904,0.005323863,0.1930006,0.3854553,0.007914762,0.275059,0.0009549964],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5092739,0.0006946746,0.2952671,0.1872372,0.005179998,0.001579555,0.000416929,0.00007808264,0.0002725498],"genre_scores_gemma":[0.9856668,0.0003354121,0.007377361,0.006052479,0.0005111848,0.000005669266,0.000004138455,0.000007779378,0.00003919055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6880628,"threshold_uncertainty_score":0.2364214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1044155246289297,"score_gpt":0.3924769315784105,"score_spread":0.2880614069494807,"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."}}