{"id":"W3116132399","doi":"10.1186/s12859-020-03848-0","title":"Deep learning detection of informative features in tau PET for Alzheimer’s disease classification","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Servier; National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Entorhinal cortex; Positron emission tomography; Temporal lobe; Neuroscience; Alzheimer's disease; Neuroimaging; Medicine; Dementia; Artificial intelligence; Voxel; Deep learning; Temporal cortex; Psychology; Disease; Pathology; Hippocampus; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001298123,0.001095157,0.0007087036,0.001072507,0.0002694568,0.0006107308,0.0008348111,0.001070321,0.0007764957],"category_scores_gemma":[0.002439475,0.0003648919,0.001026622,0.0006938784,0.0003883113,0.0005712258,0.000643578,0.001081622,0.0003636194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009348823,"about_ca_system_score_gemma":0.001021496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008084101,"about_ca_topic_score_gemma":0.006376633,"domain_scores_codex":[0.9996524,0.00008079071,0.00002465188,0.00009457515,0.00007410761,0.00007344127],"domain_scores_gemma":[0.999423,0.0002454444,0.00008522216,0.00005758847,0.0001552029,0.00003350489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003759561,0.0004145254,0.01470012,0.0001741236,0.0002922916,0.0003424533,0.00009380563,0.4486309,0.03289779,0.001899884,0.005179698,0.4949985],"study_design_scores_gemma":[0.000006513973,0.00003696158,0.00132851,0.0000099197,0.00001986918,0.00003935715,0.000005388955,0.9934344,0.003655299,0.001203464,0.000253944,0.00000632723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3058297,0.00239118,0.6854052,0.0007729132,0.0001130199,0.0001764509,0.0008759056,0.002584351,0.001851241],"genre_scores_gemma":[0.9100198,0.0004573283,0.08673583,0.0001903076,0.00005289996,0.0001074513,0.00110996,0.00004962605,0.001276696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008084101,"threshold_uncertainty_score":0.01607406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04760083672193349,"score_gpt":0.3236986725723198,"score_spread":0.2760978358503863,"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."}}